Add flush_audio() to LMNTTTSService

Add placeholders for Gladia's set_model and set_language methods
Add flush_audio() to PlayHTTTSService
2025-03-07 15:42:31 -05:00 · 2025-03-07 15:38:23 -05:00 · 2025-03-07 15:26:47 -05:00 · 2025-03-07 15:18:10 -05:00 · 2025-03-07 15:07:50 -05:00 · 2025-03-07 14:28:19 -05:00
162 changed files with 2375 additions and 5996 deletions
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -9,104 +9,11 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0

 ### Added

- ElevenLabs TTS services now support a sample rate of 8000.
+- Added a `flush_audio()` method to `AzureTTSService`, `FishTTSService`,
+  `PlayHTTTSService`, and `LMNTTTSService`.

-### Fixed
-
- Fixed an issue where the `RTVIObserver` would report two bot started and
-  stopped speaking events for each bot turn.
-
- Fixed an issue in `UltravoxSTTService` that caused improper audio processing
-  and incorrect LLM frame output.
-
-### Other
-
- Added `examples/foundational/07x-interruptible-local.py` to show how a local
-  transport can be used.
-
-## [0.0.60] - 2025-03-20
-
-### Added
-
- Added `default_headers` parameter to `BaseOpenAILLMService` constructor.
-
-### Changed
-
- Rollback to `deepgram-sdk` 3.8.0 since 3.10.1 was causing connections issues.
-
- Changed the default `InputAudioTranscription` model to `gpt-4o-transcribe`
-  for `OpenAIRealtimeBetaLLMService`.
-
-### Other
-
- Update the `19-openai-realtime-beta.py` and `19a-azure-realtime-beta.py`
-  examples to use the FunctionSchema format.
-
-## [0.0.59] - 2025-03-20
-
-### Added
-
- When registering a function call it is now possible to indicate if you want
-  the function call to be cancelled if there's a user interruption via
-  `cancel_on_interruption` (defaults to False). This is now possible because
-  function calls are executed concurrently.
-
- Added support for detecting idle pipelines. By default, if no activity has
-  been detected during 5 minutes, the `PipelineTask` will be automatically
-  cancelled. It is possible to override this behavior by passing
-  `cancel_on_idle_timeout=False`. It is also possible to change the default
-  timeout with `idle_timeout_secs` or the frames that prevent the pipeline from
-  being idle with `idle_timeout_frames`. Finally, an `on_idle_timeout` event
-  handler will be triggered if the idle timeout is reached (whether the pipeline
-  task is cancelled or not).
-
- Added `FalSTTService`, which provides STT for Fal's Wizper API.
-
- Added a `reconnect_on_error` parameter to websocket-based TTS services as well
-  as a `on_connection_error` event handler. The `reconnect_on_error` indicates
-  whether the TTS service should reconnect on error. The `on_connection_error`
-  will always get called if there's any error no matter the value of
-  `reconnect_on_error`. This allows, for example, to fallback to a different TTS
-  provider if something goes wrong with the current one.
-
- Added new `SkipTagsAggregator` that extends `BaseTextAggregator` to aggregate
-  text and skips end of sentence matching if aggregated text is between
-  start/end tags.
-
- Added new `PatternPairAggregator` that extends `BaseTextAggregator` to
-  identify content between matching pattern pairs in streamed text. This allows
-  for detection and processing of structured content like XML-style tags that
-  may span across multiple text chunks or sentence boundaries.
-
- Added new `BaseTextAggregator`. Text aggregators are used by the TTS service
-  to aggregate LLM tokens and decide when the aggregated text should be pushed
-  to the TTS service. They also allow for the text to be manipulated while it's
-  being aggregated. A text aggregator can be passed via `text_aggregator` to the
-  TTS service.
-
- Added new `sample_rate` constructor parameter to `TavusVideoService` to allow
-  changing the output sample rate.
-
- Added new `NeuphonicTTSService`.
-  (see https://neuphonic.com)
-
- Added new `UltravoxSTTService`.
-  (see https://github.com/fixie-ai/ultravox)
-
- Added `on_frame_reached_upstream` and `on_frame_reached_downstream` event
-  handlers to `PipelineTask`. Those events will be called when a frame reaches
-  the beginning or end of the pipeline respectively. Note that by default, the
-  event handlers will not be called unless a filter is set with
-  `PipelineTask.set_reached_upstream_filter()` or
-  `PipelineTask.set_reached_downstream_filter()`.
-
- Added support for Chirp voices in `GoogleTTSService`.
-
- Added a `flush_audio()` method to `FishTTSService` and `LmntTTSService`.
-
- Added a `set_language` convenience method for `GoogleSTTService`, allowing
-  you to set a single language. This is in addition to the `set_languages`
-  method which allows you to set a list of languages.
+- Added `set_language()` and `set_model()` to `AzureSTTService`,
+  `AssemblySTTService`, and `GladiaSTTService`.

 - Added `on_user_turn_audio_data` and `on_bot_turn_audio_data` to
  `AudioBufferProcessor`. This gives the ability to grab the audio of only that
@@ -164,175 +71,15 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Added `AzureRealtimeBetaLLMService` to support Azure's OpeanAI Realtime API. Added
  foundational example `19a-azure-realtime-beta.py`.

- Introduced `GoogleVertexLLMService`, a new class for integrating with Vertex AI
-  Gemini models. Added foundational example
-  `14p-function-calling-gemini-vertex-ai.py`.
-
- Added support in `OpenAIRealtimeBetaLLMService` for a slate of new features:
-
-  - The `'gpt-4o-transcribe'` input audio transcription model, along
-    with new `language` and `prompt` options specific to that model.
-  - The `input_audio_noise_reduction` session property.
-
-    ```python
-    session_properties = SessionProperties(
-      # ...
-      input_audio_noise_reduction=InputAudioNoiseReduction(
-        type="near_field" # also supported: "far_field"
-      )
-      # ...
-    )
-    ```
-
-  - The `'semantic_vad'` `turn_detection` session property value, a more
-    sophisticated model for detecting when the user has stopped speaking.
-  - `on_conversation_item_created` and `on_conversation_item_updated`
-    events to `OpenAIRealtimeBetaLLMService`.
-
-    ```python
-    @llm.event_handler("on_conversation_item_created")
-    async def on_conversation_item_created(llm, item_id, item):
-      # ...
-
-    @llm.event_handler("on_conversation_item_updated")
-    async def on_conversation_item_updated(llm, item_id, item):
-      # `item` may not always be available here
-      # ...
-    ```
-
-  - The `retrieve_conversation_item(item_id)` method for introspecting a
-    conversation item on the server.
-
-    ```python
-    item = await llm.retrieve_conversation_item(item_id)
-    ```
-
 ### Changed

- Updated `OpenAISTTService` to use `gpt-4o-transcribe` as the default
-  transcription model.
-
- Updated `OpenAITTSService` to use `gpt-4o-mini-tts` as the default TTS model.
-
- Function calls are now executed in tasks. This means that the pipeline will
-  not be blocked while the function call is being executed.
-
- ⚠️ `PipelineTask` will now be automatically cancelled if no bot activity is
-  happening in the pipeline. There are a few settings to configure this
-  behavior, see `PipelineTask` documentation for more details.
-
- All event handlers are now executed in separate tasks in order to prevent
-  blocking the pipeline. It is possible that event handlers take some time to
-  execute in which case the pipeline would be blocked waiting for the event
-  handler to complete.
-
- Updated `TranscriptProcessor` to support text output from
-  `OpenAIRealtimeBetaLLMService`.
-
- `OpenAIRealtimeBetaLLMService` and `GeminiMultimodalLiveLLMService` now push
-  a `TTSTextFrame`.
-
- Updated the default mode for `CartesiaTTSService` and
-  `CartesiaHttpTTSService` to `sonic-2`.
-
-### Deprecated
-
- Passing a `start_callback` to `LLMService.register_function()` is now
-  deprecated, simply move the code from the start callback to the function call.
-
- `TTSService` parameter `text_filter` is now deprecated, use `text_filters`
-  instead which is now a list. This allows passing multiple filters that will be
-  executed in order.
-
-### Removed
-
- Removed deprecated `audio.resample_audio()`, use `create_default_resampler()`
-  instead.
-
- Removed deprecated`stt_service` parameter from `STTMuteFilter`.
-
- Removed deprecated RTVI processors, use an `RTVIObserver` instead.
-
- Removed deprecated `AWSTTSService`, use `PollyTTSService` instead.
-
- Removed deprecated field `tier` from `DailyTranscriptionSettings`, use `model`
-  instead.
-
- Removed deprecated `pipecat.vad` package, use `pipecat.audio.vad` instead.
+- Moved `flush_audio()` from the `TTSService` base class to
+  `WebsocketTTSService`.

 ### Fixed

- Fixed an assistant aggregator issue that could cause assistant text to be
-  split into multiple chunks during function calls.
-
- Fixed an assistant aggregator issue that was causing assistant text to not be
-  added to the context during function calls. This could lead to duplications.
-
- Fixed a `SegmentedSTTService` issue that was causing audio to be sent
-  prematurely to the STT service. Instead of analyzing the volume in this
-  service we rely on VAD events which use both VAD and volume.
-
- Fixed a `GeminiMultimodalLiveLLMService` issue that was causing messages to be
-  duplicated in the context when pushing `LLMMessagesAppendFrame` frames.
-
- Fixed an issue with `SegmentedSTTService` based services
-  (e.g. `GroqSTTService`) that was not allow audio to pass-through downstream.
-
- Fixed a `CartesiaTTSService` and `RimeTTSService` issue that would consider
-  text between spelling out tags end of sentence.
-
- Fixed a `match_endofsentence` issue that would result in floating point
-  numbers to be considered an end of sentence.
-
- Fixed a `match_endofsentence` issue that would result in emails to be
-  considered an end of sentence.
-
- Fixed an issue where the RTVI message `disconnect-bot` was pushing an
-  `EndFrame`, resulting in the pipeline not shutting down. It now pushes an
-  `EndTaskFrame` upstream to shutdown the pipeline.
-
- Fixed an issue with the `GoogleSTTService` where stream timeouts during
-  periods of inactivity were causing connection failures. The service now
-  properly detects timeout errors and handles reconnection gracefully,
-  ensuring continuous operation even after periods of silence or when using an
-  `STTMuteFilter`.
-
- Fixed an issue in `RimeTTSService` where the last line of text sent didn't
-  result in an audio output being generated.
-
- Fixed `OpenAIRealtimeBetaLLMService` by adding proper handling for:
-  - The `conversation.item.input_audio_transcription.delta` server message,
-    which was added server-side at some point and not handled client-side.
-  - Errors reported by the `response.done` server message.
-
-### Other
-
- Add foundational example `07w-interruptible-fal.py`, showing `FalSTTService`.
-
- Added a new Ultravox example
-  `examples/foundational/07u-interruptible-ultravox.py`.
-
- Added new Neuphonic examples
-  `examples/foundational/07v-interruptible-neuphonic.py` and
-  `examples/foundational/07v-interruptible-neuphonic-http.py`.
-
- Added a new example `examples/foundational/36-user-email-gathering.py` to show
-  how to gather user emails. The example uses's Cartesia's `<spell></spell>`
-  tags and Rime `spell()` function to spell out the emails for confirmation.
-
- Update the `34-audio-recording.py` example to include an STT processor.
-
- Added foundational example `35-voice-switching.py` showing how to use the new
-  `PatternPairAggregator`. This example shows how to encode information for the
-  LLM to instruct TTS voice changes, but this can be used to encode any
-  information into the LLM response, which you want to parse and use in other
-  parts of your application.
-
- Added a Pipecat Cloud deployment example to the `examples` directory.
-
- Removed foundational examples 28b and 28c as the TranscriptProcessor no
-  longer has an LLM depedency. Renamed foundational example 28a to
-  `28-transcript-processor.py`.
+- Fixed an issue in `GoogleSTTService`, where it didn't have a `set_language`
+  function. This required a name change from `set_languages` to `set_language`.

 ## [0.0.58] - 2025-02-26

@@ -414,9 +161,6 @@ stt = DeepgramSTTService(..., live_options=LiveOptions(model="nova-2-general"))

 ### Fixed

- Fixed an issue that would cause undesired interruptions via
-  `EmulateUserStartedSpeakingFrame`.
-
 - Fixed a `GoogleLLMService` that was causing an exception when sending inline
  audio in some cases.

@@ -433,6 +177,10 @@ stt = DeepgramSTTService(..., live_options=LiveOptions(model="nova-2-general"))

 - Fixed `match_endofsentence` support for ellipses.

+- Fixed an issue that would cause undesired interruptions via
+  `EmulateUserStartedSpeakingFrame` when only interim transcriptions (i.e. no
+  final transcriptions) where received.
+
 - Fixed an issue where `EndTaskFrame` was not triggering
  `on_client_disconnected` or closing the WebSocket in FastAPI.

@@ -2097,7 +1845,7 @@ async def on_connected(processor):
  completed. If a task is never ran `has_finished()` will return False.

 - `PipelineRunner` now supports SIGTERM. If received, the runner will be
-  cancelled.
+  canceled.

 ### Fixed

--- a/README.md
+++ b/README.md
@@ -57,13 +57,13 @@ pip install "pipecat-ai[option,...]"

 | Category            | Services                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                | Install Command Example                 |
 | ------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------- |
-| Speech-to-Text      | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [Fal Wizper](https://docs.pipecat.ai/server/services/stt/fal), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [Parakeet (NVIDIA)](https://docs.pipecat.ai/server/services/stt/parakeet), [Ultravox](https://docs.pipecat.ai/server/services/stt/ultravox), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper)                                                                                                                                                                                  | `pip install "pipecat-ai[deepgram]"`    |
+| Speech-to-Text      | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper)                                                                                                                                                                                                                                                                                                                                                                                              | `pip install "pipecat-ai[deepgram]"`    |
 | LLMs                | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [Azure](https://docs.pipecat.ai/server/services/llm/azure), [Cerebras](https://docs.pipecat.ai/server/services/llm/cerebras), [DeepSeek](https://docs.pipecat.ai/server/services/llm/deepseek), [Fireworks AI](https://docs.pipecat.ai/server/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/server/services/llm/gemini), [Grok](https://docs.pipecat.ai/server/services/llm/grok), [Groq](https://docs.pipecat.ai/server/services/llm/groq), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nim), [Ollama](https://docs.pipecat.ai/server/services/llm/ollama), [OpenAI](https://docs.pipecat.ai/server/services/llm/openai), [OpenRouter](https://docs.pipecat.ai/server/services/llm/openrouter), [Perplexity](https://docs.pipecat.ai/server/services/llm/perplexity), [Together AI](https://docs.pipecat.ai/server/services/llm/together) | `pip install "pipecat-ai[openai]"`      |
-| Text-to-Speech      | [AWS](https://docs.pipecat.ai/server/services/tts/aws), [Azure](https://docs.pipecat.ai/server/services/tts/azure), [Cartesia](https://docs.pipecat.ai/server/services/tts/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/tts/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/tts/elevenlabs), [FastPitch (NVIDIA)](https://docs.pipecat.ai/server/services/tts/fastpitch), [Fish](https://docs.pipecat.ai/server/services/tts/fish), [Google](https://docs.pipecat.ai/server/services/tts/google), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [Neuphonic](https://docs.pipecat.ai/server/services/tts/neuphonic), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [PlayHT](https://docs.pipecat.ai/server/services/tts/playht), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts)                         | `pip install "pipecat-ai[cartesia]"`    |
+| Text-to-Speech      | [AWS](https://docs.pipecat.ai/server/services/tts/aws), [Azure](https://docs.pipecat.ai/server/services/tts/azure), [Cartesia](https://docs.pipecat.ai/server/services/tts/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/tts/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/tts/elevenlabs), [Fish](https://docs.pipecat.ai/server/services/tts/fish), [Google](https://docs.pipecat.ai/server/services/tts/google), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [PlayHT](https://docs.pipecat.ai/server/services/tts/playht), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts)                                                                                                                                                                          | `pip install "pipecat-ai[cartesia]"`    |
 | Speech-to-Speech    | [Gemini Multimodal Live](https://docs.pipecat.ai/server/services/s2s/gemini), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     | `pip install "pipecat-ai[google]"`      |
 | Transport           | [Daily (WebRTC)](https://docs.pipecat.ai/server/services/transport/daily), [FastAPI Websocket](https://docs.pipecat.ai/server/services/transport/fastapi-websocket), [WebSocket Server](https://docs.pipecat.ai/server/services/transport/websocket-server), Local                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      | `pip install "pipecat-ai[daily]"`       |
 | Video               | [Tavus](https://docs.pipecat.ai/server/services/video/tavus), [Simli](https://docs.pipecat.ai/server/services/video/simli)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              | `pip install "pipecat-ai[tavus,simli]"` |
-| Vision & Image      | [fal](https://docs.pipecat.ai/server/services/image-generation/fal), [Google Imagen](https://docs.pipecat.ai/server/services/image-generation/fal), [Moondream](https://docs.pipecat.ai/server/services/vision/moondream)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               | `pip install "pipecat-ai[moondream]"`   |
+| Vision & Image      | [Moondream](https://docs.pipecat.ai/server/services/vision/moondream), [fal](https://docs.pipecat.ai/server/services/image-generation/fal)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              | `pip install "pipecat-ai[moondream]"`   |
 | Audio Processing    | [Silero VAD](https://docs.pipecat.ai/server/utilities/audio/silero-vad-analyzer), [Krisp](https://docs.pipecat.ai/server/utilities/audio/krisp-filter), [Koala](https://docs.pipecat.ai/server/utilities/audio/koala-filter), [Noisereduce](https://docs.pipecat.ai/server/utilities/audio/noisereduce-filter)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          | `pip install "pipecat-ai[silero]"`      |
 | Analytics & Metrics | [Canonical AI](https://docs.pipecat.ai/server/services/analytics/canonical), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         | `pip install "pipecat-ai[canonical]"`   |

--- a/dev-requirements.txt
+++ b/dev-requirements.txt
@@ -3,10 +3,10 @@ coverage~=7.6.12
 grpcio-tools~=1.67.1
 pip-tools~=7.4.1
 pre-commit~=4.0.1
-pyright~=1.1.397
+pyright~=1.1.394
 pytest~=8.3.4
 pytest-asyncio~=0.25.3
-ruff~=0.11.1
+ruff~=0.9.7
 setuptools~=70.0.0
 setuptools_scm~=8.1.0
 python-dotenv~=1.0.1
--- a/dot-env.template
+++ b/dot-env.template
@@ -29,9 +29,6 @@ DAILY_SAMPLE_ROOM_URL=https://...
 ELEVENLABS_API_KEY=...
 ELEVENLABS_VOICE_ID=...

-# Neuphonic
-NEUPHONIC_API_KEY=...
-
 # Fal
 FAL_KEY=...

--- a/examples/bot-ready-signalling/server/signalling_bot.py
+++ b/examples/bot-ready-signalling/server/signalling_bot.py
@@ -64,7 +64,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        runner = PipelineRunner()
--- a/examples/deployment/modal-example/bot.py
+++ b/examples/deployment/modal-example/bot.py
@@ -34,7 +34,7 @@ async def main(room_url: str, token: str):
    )

    tts = CartesiaTTSService(
-        api_key=os.getenv("CARTESIA_API_KEY", ""), voice_id="71a7ad14-091c-4e8e-a314-022ece01c121"
+        api_key=os.getenv("CARTESIA_API_KEY", ""), voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22"
    )

    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
--- a/examples/deployment/pipecat-cloud-example/.gitignore
+++ b/examples/deployment/pipecat-cloud-example/.gitignore
@@ -1,94 +0,0 @@
-# Python
-__pycache__/
-*.py[cod]
-*$py.class
-*.so
-.Python
-build/
-dist/
-*.egg-info/
-*.egg
-.installed.cfg
-.eggs/
-downloads/
-lib/
-lib64/
-parts/
-sdist/
-var/
-wheels/
-share/python-wheels/
-MANIFEST
-
-# Virtual Environments
-venv/
-env/
-.env
-.venv/
-ENV/
-env.bak/
-venv.bak/
-
-# IDE
-.idea/
-.vscode/
-.spyderproject
-.spyproject
-.ropeproject
-
-# Testing and Coverage
-.coverage
-.coverage.*
-htmlcov/
-.pytest_cache/
-.tox/
-.nox/
-.cache
-nosetests.xml
-coverage.xml
-*.cover
-.hypothesis/
-cover/
-
-# Logs and Databases
-*.log
-*.db
-db.sqlite3
-db.sqlite3-journal
-pip-log.txt
-
-# System Files
-.DS_Store
-Thumbs.db
-desktop.ini
-*.swp
-*.swo
-*.bak
-*.tmp
-*~
-
-# Build and Documentation
-docs/_build/
-.pybuilder/
-target/
-instance/
-.webassets-cache
-.pdm.toml
-.pdm-python
-.pdm-build/
-__pypackages__/
-
-# Other
-*.mo
-*.pot
-*.sage.py
-.mypy_cache/
-.dmypy.json
-dmypy.json
-.pyre/
-.pytype/
-cython_debug/
-.ipynb_checkpoints
-
-# Pipecat cloud
-.pcc-deploy.toml
--- a/examples/deployment/pipecat-cloud-example/Dockerfile
+++ b/examples/deployment/pipecat-cloud-example/Dockerfile
@@ -1,7 +0,0 @@
-FROM dailyco/pipecat-base:latest
-
-COPY ./requirements.txt requirements.txt
-
-RUN pip install --no-cache-dir --upgrade -r requirements.txt
-
-COPY ./bot.py bot.py
--- a/examples/deployment/pipecat-cloud-example/README.md
+++ b/examples/deployment/pipecat-cloud-example/README.md
@@ -1,196 +0,0 @@
-# Pipecat Cloud Starter Project
-
-[![Docs](https://img.shields.io/badge/Documentation-blue)](https://docs.pipecat.daily.co) [![Discord](https://img.shields.io/discord/1217145424381743145)](https://discord.gg/dailyco)
-
-A template voice agent for [Pipecat Cloud](https://www.daily.co/products/pipecat-cloud/) that demonstrates building and deploying a conversational AI agent.
-
-> **For a detailed step-by-step guide, see our [Quickstart Documentation](https://docs.pipecat.daily.co/quickstart).**
-
-## Prerequisites
-
- Python 3.10+
- Linux, MacOS, or Windows Subsystem for Linux (WSL)
- [Docker](https://www.docker.com) and a Docker repository (e.g., [Docker Hub](https://hub.docker.com))
- A Docker Hub account (or other container registry account)
- [Pipecat Cloud](https://pipecat.daily.co) account
-
-> **Note**: If you haven't installed Docker yet, follow the official installation guides for your platform ([Linux](https://docs.docker.com/engine/install/), [Mac](https://docs.docker.com/desktop/setup/install/mac-install/), [Windows](https://docs.docker.com/desktop/setup/install/windows-install/)). For Docker Hub, [create a free account](https://hub.docker.com/signup) and log in via terminal with `docker login`.
-
-## Get Started
-
-### 1. Get the starter project
-
-Clone the starter project from GitHub:
-
-```bash
-git clone https://github.com/daily-co/pipecat-cloud-starter
-cd pipecat-cloud-starter
-```
-
-### 2. Set up your Python environment
-
-We recommend using a virtual environment to manage your Python dependencies.
-
-```bash
-# Create a virtual environment
-python -m venv .venv
-
-# Activate it
-source .venv/bin/activate  # On Windows: .venv\Scripts\activate
-
-# Install the Pipecat Cloud CLI
-pip install pipecatcloud
-```
-
-### 3. Authenticate with Pipecat Cloud
-
-```bash
-pcc auth login
-```
-
-### 4. Acquire required API keys
-
-This starter requires the following API keys:
-
- **OpenAI API Key**: Get from [platform.openai.com/api-keys](https://platform.openai.com/api-keys)
- **Cartesia API Key**: Get from [play.cartesia.ai/keys](https://play.cartesia.ai/keys)
- **Daily API Key**: Automatically provided through your Pipecat Cloud account
-
-### 5. Configure to run locally (optional)
-
-You can test your agent locally before deploying to Pipecat Cloud:
-
-```bash
-# Set environment variables with your API keys
-export CARTESIA_API_KEY="your_cartesia_key"
-export DAILY_API_KEY="your_daily_key"
-export OPENAI_API_KEY="your_openai_key"
-```
-
-> Your `DAILY_API_KEY` can be found at [https://pipecat.daily.co](https://pipecat.daily.co) under the `Settings` in the `Daily (WebRTC)` tab.
-
-First install requirements:
-
-```bash
-pip install -r requirements.txt
-```
-
-Then, launch the bot.py script locally:
-
-```bash
-LOCAL_RUN=1 python bot.py
-```
-
-## Deploy & Run
-
-### 1. Build and push your Docker image
-
-```bash
-# Build the image (targeting ARM architecture for cloud deployment)
-docker build --platform=linux/arm64 -t my-first-agent:latest .
-
-# Tag with your Docker username and version
-docker tag my-first-agent:latest your-username/my-first-agent:0.1
-
-# Push to Docker Hub
-docker push your-username/my-first-agent:0.1
-```
-
-### 2. Create a secret set for your API keys
-
-The starter project requires API keys for OpenAI and Cartesia:
-
-```bash
-# Copy the example env file
-cp env.example .env
-
-# Edit .env to add your API keys:
-# CARTESIA_API_KEY=your_cartesia_key
-# OPENAI_API_KEY=your_openai_key
-
-# Create a secret set from your .env file
-pcc secrets set my-first-agent-secrets --file .env
-```
-
-Alternatively, you can create secrets directly via CLI:
-
-```bash
-pcc secrets set my-first-agent-secrets \
-  CARTESIA_API_KEY=your_cartesia_key \
-  OPENAI_API_KEY=your_openai_key
-```
-
-### 3. Deploy to Pipecat Cloud
-
-```bash
-pcc deploy my-first-agent your-username/my-first-agent:0.1 --secrets my-first-agent-secrets
-```
-
-> **Note (Optional)**: For a more maintainable approach, you can use the included `pcc-deploy.toml` file:
->
-> ```toml
-> agent_name = "my-first-agent"
-> image = "your-username/my-first-agent:0.1"
-> secret_set = "my-first-agent-secrets"
->
-> [scaling]
->     min_instances = 0
-> ```
->
-> Then simply run `pcc deploy` without additional arguments.
-
-> **Note**: If your repository is private, you'll need to add credentials:
->
-> ```bash
-> # Create pull secret (you’ll be prompted for credentials)
-> pcc secrets image-pull-secret pull-secret https://index.docker.io/v1/
->
-> # Deploy with credentials
-> pcc deploy my-first-agent your-username/my-first-agent:0.1 --credentials pull-secret
-> ```
-
-### 4. Check deployment and scaling (optional)
-
-By default, your agent will use "scale-to-zero" configuration, which means it may have a cold start of around 10 seconds when first used. By default, idle instances are maintained for 5 minutes before being terminated when using scale-to-zero.
-
-For more responsive testing, you can scale your deployment to keep a minimum of one instance warm:
-
-```bash
-# Ensure at least one warm instance is always available
-pcc deploy my-first-agent your-username/my-first-agent:0.1 --min-instances 1
-
-# Check the status of your deployment
-pcc agent status my-first-agent
-```
-
-By default, idle instances are maintained for 5 minutes before being terminated when using scale-to-zero.
-
-### 5. Create an API key
-
-```bash
-# Create a public API key for accessing your agent
-pcc organizations keys create
-
-# Set it as the default key to use with your agent
-pcc organizations keys use
-```
-
-### 6. Start your agent
-
-```bash
-# Start a session with your agent in a Daily room
-pcc agent start my-first-agent --use-daily
-```
-
-This will return a URL, which you can use to connect to your running agent.
-
-## Documentation
-
-For more details on Pipecat Cloud and its capabilities:
-
- [Pipecat Cloud Documentation](https://docs.pipecat.daily.co)
- [Pipecat Project Documentation](https://docs.pipecat.ai)
-
-## Support
-
-Join our [Discord community](https://discord.gg/dailyco) for help and discussions.
--- a/examples/deployment/pipecat-cloud-example/bot.py
+++ b/examples/deployment/pipecat-cloud-example/bot.py
@@ -1,161 +0,0 @@
-#
-# Copyright (c) 2025, Daily
-#
-# SPDX-License-Identifier: BSD 2-Clause License
-#
-
-import os
-
-import aiohttp
-from dotenv import load_dotenv
-from loguru import logger
-from pipecatcloud.agent import DailySessionArguments
-
-from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame
-from pipecat.pipeline.pipeline import Pipeline
-from pipecat.pipeline.runner import PipelineRunner
-from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
-from pipecat.services.cartesia import CartesiaTTSService
-from pipecat.services.openai import OpenAILLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
-
-# Check if we're in local development mode
-LOCAL_RUN = os.getenv("LOCAL_RUN")
-if LOCAL_RUN:
-    import asyncio
-    import webbrowser
-
-    try:
-        from local_runner import configure
-    except ImportError:
-        logger.error("Could not import local_runner module. Local development mode may not work.")
-
-# Load environment variables
-load_dotenv(override=True)
-
-
-async def main(room_url: str, token: str):
-    """Main pipeline setup and execution function.
-
-    Args:
-        room_url: The Daily room URL
-        token: The Daily room token
-    """
-    logger.debug("Starting bot in room: {}", room_url)
-
-    transport = DailyTransport(
-        room_url,
-        token,
-        "bot",
-        DailyParams(
-            audio_out_enabled=True,
-            transcription_enabled=True,
-            vad_enabled=True,
-            vad_analyzer=SileroVADAnalyzer(),
-        ),
-    )
-
-    tts = CartesiaTTSService(
-        api_key=os.getenv("CARTESIA_API_KEY"), voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22"
-    )
-
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
-
-    messages = [
-        {
-            "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-        },
-    ]
-
-    context = OpenAILLMContext(messages)
-    context_aggregator = llm.create_context_aggregator(context)
-
-    pipeline = Pipeline(
-        [
-            transport.input(),
-            context_aggregator.user(),
-            llm,
-            tts,
-            transport.output(),
-            context_aggregator.assistant(),
-        ]
-    )
-
-    task = PipelineTask(
-        pipeline,
-        params=PipelineParams(
-            allow_interruptions=True,
-            enable_metrics=True,
-            enable_usage_metrics=True,
-            report_only_initial_ttfb=True,
-        ),
-    )
-
-    @transport.event_handler("on_first_participant_joined")
-    async def on_first_participant_joined(transport, participant):
-        logger.info("First participant joined: {}", participant["id"])
-        await transport.capture_participant_transcription(participant["id"])
-        # Kick off the conversation.
-        messages.append(
-            {
-                "role": "system",
-                "content": "Please start with 'Hello World' and introduce yourself to the user.",
-            }
-        )
-        await task.queue_frames([LLMMessagesFrame(messages)])
-
-    @transport.event_handler("on_participant_left")
-    async def on_participant_left(transport, participant, reason):
-        logger.info("Participant left: {}", participant)
-        await task.cancel()
-
-    runner = PipelineRunner()
-
-    await runner.run(task)
-
-
-async def bot(args: DailySessionArguments):
-    """Main bot entry point compatible with the FastAPI route handler.
-
-    Args:
-        room_url: The Daily room URL
-        token: The Daily room token
-        body: The configuration object from the request body
-        session_id: The session ID for logging
-    """
-    logger.info(f"Bot process initialized {args.room_url} {args.token}")
-
-    try:
-        await main(args.room_url, args.token)
-        logger.info("Bot process completed")
-    except Exception as e:
-        logger.exception(f"Error in bot process: {str(e)}")
-        raise
-
-
-# Local development functions
-async def local_main():
-    """Function for local development testing."""
-    try:
-        async with aiohttp.ClientSession() as session:
-            (room_url, token) = await configure(session)
-            logger.warning("_")
-            logger.warning("_")
-            logger.warning(f"Talk to your voice agent here: {room_url}")
-            logger.warning("_")
-            logger.warning("_")
-            webbrowser.open(room_url)
-            await main(room_url, token)
-    except Exception as e:
-        logger.exception(f"Error in local development mode: {e}")
-
-
-# Local development entry point
-if LOCAL_RUN and __name__ == "__main__":
-    try:
-        asyncio.run(local_main())
-    except Exception as e:
-        logger.exception(f"Failed to run in local mode: {e}")
--- a/examples/deployment/pipecat-cloud-example/env.example
+++ b/examples/deployment/pipecat-cloud-example/env.example
@@ -1,2 +0,0 @@
-CARTESIA_API_KEY=
-OPENAI_API_KEY=
--- a/examples/deployment/pipecat-cloud-example/local_runner.py
+++ b/examples/deployment/pipecat-cloud-example/local_runner.py
@@ -1,46 +0,0 @@
-#
-# Copyright (c) 2024–2025, Daily
-#
-# SPDX-License-Identifier: BSD 2-Clause License
-#
-
-import os
-
-import aiohttp
-
-from pipecat.transports.services.helpers.daily_rest import DailyRESTHelper, DailyRoomParams
-
-
-async def configure(aiohttp_session: aiohttp.ClientSession):
-    (url, token) = await configure_with_args(aiohttp_session)
-    return (url, token)
-
-
-async def configure_with_args(aiohttp_session: aiohttp.ClientSession = None):
-    key = os.getenv("DAILY_API_KEY")
-    if not key:
-        raise Exception(
-            "No Daily API key specified. set DAILY_API_KEY in your environment to specify a Daily API key, available from https://dashboard.daily.co/developers."
-        )
-
-    daily_rest_helper = DailyRESTHelper(
-        daily_api_key=key,
-        daily_api_url=os.getenv("DAILY_API_URL", "https://api.daily.co/v1"),
-        aiohttp_session=aiohttp_session,
-    )
-
-    room = await daily_rest_helper.create_room(
-        DailyRoomParams(properties={"enable_prejoin_ui": False})
-    )
-    if not room.url:
-        raise HTTPException(status_code=500, detail="Failed to create room")
-
-    url = room.url
-
-    # Create a meeting token for the given room with an expiration 1 hour in
-    # the future.
-    expiry_time: float = 60 * 60
-
-    token = await daily_rest_helper.get_token(url, expiry_time)
-
-    return (url, token)
--- a/examples/deployment/pipecat-cloud-example/pcc-deploy.toml
+++ b/examples/deployment/pipecat-cloud-example/pcc-deploy.toml
@@ -1,6 +0,0 @@
-agent_name = "my-first-agent"
-image = "your-username/my-first-agent:0.1"
-secret_set = "my-first-agent-secrets"
-
-[scaling]
-	min_instances = 0
--- a/examples/deployment/pipecat-cloud-example/requirements.txt
+++ b/examples/deployment/pipecat-cloud-example/requirements.txt
@@ -1,3 +0,0 @@
-pipecatcloud
-pipecat-ai[cartesia,daily,openai,silero]>=0.0.58
-python-dotenv~=1.0.1
--- a/examples/foundational/01-say-one-thing.py
+++ b/examples/foundational/01-say-one-thing.py
@@ -36,7 +36,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        runner = PipelineRunner()
--- a/examples/foundational/01a-local-audio.py
+++ b/examples/foundational/01a-local-audio.py
@@ -29,7 +29,7 @@ async def main():

    tts = CartesiaTTSService(
        api_key=os.getenv("CARTESIA_API_KEY"),
-        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
    )

    pipeline = Pipeline([tts, transport.output()])
--- a/examples/foundational/01b-livekit-audio.py
+++ b/examples/foundational/01b-livekit-audio.py
@@ -83,7 +83,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        runner = PipelineRunner()
--- a/examples/foundational/02-llm-say-one-thing.py
+++ b/examples/foundational/02-llm-say-one-thing.py
@@ -37,7 +37,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
--- a/examples/foundational/05-sync-speech-and-image.py
+++ b/examples/foundational/05-sync-speech-and-image.py
@@ -87,7 +87,7 @@ async def main():

        tts = CartesiaHttpTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        imagegen = FalImageGenService(
--- a/examples/foundational/05a-local-sync-speech-and-image.py
+++ b/examples/foundational/05a-local-sync-speech-and-image.py
@@ -97,7 +97,7 @@ async def main():

            tts = CartesiaHttpTTSService(
                api_key=os.getenv("CARTESIA_API_KEY"),
-                voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+                voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
            )

            imagegen = FalImageGenService(
--- a/examples/foundational/06-listen-and-respond.py
+++ b/examples/foundational/06-listen-and-respond.py
@@ -74,7 +74,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
--- a/examples/foundational/06a-image-sync.py
+++ b/examples/foundational/06a-image-sync.py
@@ -93,7 +93,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
--- a/examples/foundational/07-interruptible-vad.py
+++ b/examples/foundational/07-interruptible-vad.py
@@ -47,7 +47,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
--- a/examples/foundational/07-interruptible.py
+++ b/examples/foundational/07-interruptible.py
@@ -46,7 +46,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
--- a/examples/foundational/07a-interruptible-anthropic.py
+++ b/examples/foundational/07a-interruptible-anthropic.py
@@ -46,7 +46,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        llm = AnthropicLLMService(
--- a/examples/foundational/07b-interruptible-langchain.py
+++ b/examples/foundational/07b-interruptible-langchain.py
@@ -64,7 +64,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        prompt = ChatPromptTemplate.from_messages(
--- a/examples/foundational/07g-interruptible-openai.py
+++ b/examples/foundational/07g-interruptible-openai.py
@@ -51,20 +51,16 @@ async def main():
        #     api_key="gsk_***",
        #     model="whisper-large-v3",
        # )
-        stt = OpenAISTTService(
-            api_key=os.getenv("OPENAI_API_KEY"),
-            model="gpt-4o-transcribe-latest",
-            prompt="Expect words related to dogs, such as breed names.",
-        )
+        stt = OpenAISTTService(api_key=os.getenv("OPENAI_API_KEY"), model="whisper-1")

-        tts = OpenAITTSService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o-mini-tts-latest")
+        tts = OpenAITTSService(api_key=os.getenv("OPENAI_API_KEY"), voice="alloy")

        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")

        messages = [
            {
                "role": "system",
-                "content": "You are very knowledgable about dogs. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
            },
        ]

--- a/examples/foundational/07h-interruptible-openpipe.py
+++ b/examples/foundational/07h-interruptible-openpipe.py
@@ -47,7 +47,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        timestamp = int(time.time())
--- a/examples/foundational/07j-interruptible-gladia.py
+++ b/examples/foundational/07j-interruptible-gladia.py
@@ -21,6 +21,7 @@ from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.gladia import GladiaSTTService
 from pipecat.services.openai import OpenAILLMService
+from pipecat.transcriptions.language import Language
 from pipecat.transports.services.daily import DailyParams, DailyTransport

 load_dotenv(override=True)
@@ -51,7 +52,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
--- a/examples/foundational/07l-interruptible-together.py
+++ b/examples/foundational/07l-interruptible-together.py
@@ -46,7 +46,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        llm = TogetherLLMService(
--- a/examples/foundational/07o-interruptible-assemblyai.py
+++ b/examples/foundational/07o-interruptible-assemblyai.py
@@ -51,7 +51,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
--- a/examples/foundational/07s-interruptible-google-audio-in.py
+++ b/examples/foundational/07s-interruptible-google-audio-in.py
@@ -213,7 +213,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"), model="gemini-2.0-flash-001")
--- a/examples/foundational/07u-interruptible-ultravox.py
+++ b/examples/foundational/07u-interruptible-ultravox.py
@@ -1,91 +0,0 @@
-#
-# Copyright (c) 2024–2025, Daily
-#
-# SPDX-License-Identifier: BSD 2-Clause License
-#
-
-import asyncio
-import os
-import sys
-
-import aiohttp
-from dotenv import load_dotenv
-from loguru import logger
-from runner import configure
-
-from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
-from pipecat.pipeline.pipeline import Pipeline
-from pipecat.pipeline.runner import PipelineRunner
-from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.services.cartesia import CartesiaTTSService
-from pipecat.services.ultravox import UltravoxSTTService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
-
-load_dotenv(override=True)
-
-# NOTE: This example requires GPU resources to run efficiently.
-# The Ultravox model is compute-intensive and performs best with GPU acceleration.
-# This can be deployed on cloud GPU providers like Cerebrium.ai for optimal performance.
-
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
-
-# Want to initialize the ultravox processor since it takes time to load the model and dont
-# want to load it every time the pipeline is run
-ultravox_processor = UltravoxSTTService(
-    model_size="fixie-ai/ultravox-v0_4_1-llama-3_1-8b",
-    hf_token=os.getenv("HF_TOKEN"),
-)
-
-
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
-
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                transcription_enabled=False,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-                vad_audio_passthrough=True,
-            ),
-        )
-
-        tts = CartesiaTTSService(
-            api_key=os.environ.get("CARTESIA_API_KEY"),
-            voice_id="97f4b8fb-f2fe-444b-bb9a-c109783a857a",
-        )
-
-        pipeline = Pipeline(
-            [
-                transport.input(),  # Transport user input
-                ultravox_processor,
-                tts,  # TTS
-                transport.output(),  # Transport bot output
-            ]
-        )
-
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-            ),
-        )
-
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.cancel()
-
-        runner = PipelineRunner()
-
-        await runner.run(task)
-
-
-if __name__ == "__main__":
-    asyncio.run(main())
--- a/examples/foundational/07v-interruptible-neuphonic-http.py
+++ b/examples/foundational/07v-interruptible-neuphonic-http.py
@@ -1,102 +0,0 @@
-#
-# Copyright (c) 2024–2025, Daily
-#
-# SPDX-License-Identifier: BSD 2-Clause License
-#
-
-import asyncio
-import os
-import sys
-
-import aiohttp
-from dotenv import load_dotenv
-from loguru import logger
-from runner import configure
-
-from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.pipeline.pipeline import Pipeline
-from pipecat.pipeline.runner import PipelineRunner
-from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
-from pipecat.services.neuphonic import NeuphonicHttpTTSService
-from pipecat.services.openai import OpenAILLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
-
-load_dotenv(override=True)
-
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
-
-
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
-
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                transcription_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-            ),
-        )
-
-        tts = NeuphonicHttpTTSService(
-            api_key=os.getenv("NEUPHONIC_API_KEY"),
-            voice_id="fc854436-2dac-4d21-aa69-ae17b54e98eb",  # Emily
-        )
-
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
-
-        messages = [
-            {
-                "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-            },
-        ]
-
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
-
-        pipeline = Pipeline(
-            [
-                transport.input(),  # Transport user input
-                context_aggregator.user(),  # User responses
-                llm,  # LLM
-                tts,  # TTS
-                transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
-            ]
-        )
-
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-                report_only_initial_ttfb=True,
-            ),
-        )
-
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
-            # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
-
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.cancel()
-
-        runner = PipelineRunner()
-
-        await runner.run(task)
-
-
-if __name__ == "__main__":
-    asyncio.run(main())
--- a/examples/foundational/07v-interruptible-neuphonic.py
+++ b/examples/foundational/07v-interruptible-neuphonic.py
@@ -1,102 +0,0 @@
-#
-# Copyright (c) 2024–2025, Daily
-#
-# SPDX-License-Identifier: BSD 2-Clause License
-#
-
-import asyncio
-import os
-import sys
-
-import aiohttp
-from dotenv import load_dotenv
-from loguru import logger
-from runner import configure
-
-from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.pipeline.pipeline import Pipeline
-from pipecat.pipeline.runner import PipelineRunner
-from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
-from pipecat.services.neuphonic import NeuphonicTTSService
-from pipecat.services.openai import OpenAILLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
-
-load_dotenv(override=True)
-
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
-
-
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
-
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                transcription_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-            ),
-        )
-
-        tts = NeuphonicTTSService(
-            api_key=os.getenv("NEUPHONIC_API_KEY"),
-            voice_id="fc854436-2dac-4d21-aa69-ae17b54e98eb",  # Emily
-        )
-
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
-
-        messages = [
-            {
-                "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-            },
-        ]
-
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
-
-        pipeline = Pipeline(
-            [
-                transport.input(),  # Transport user input
-                context_aggregator.user(),  # User responses
-                llm,  # LLM
-                tts,  # TTS
-                transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
-            ]
-        )
-
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-                report_only_initial_ttfb=True,
-            ),
-        )
-
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
-            # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
-
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.cancel()
-
-        runner = PipelineRunner()
-
-        await runner.run(task)
-
-
-if __name__ == "__main__":
-    asyncio.run(main())
--- a/examples/foundational/07w-interruptible-fal.py
+++ b/examples/foundational/07w-interruptible-fal.py
@@ -1,110 +0,0 @@
-#
-# Copyright (c) 2024–2025, Daily
-#
-# SPDX-License-Identifier: BSD 2-Clause License
-#
-
-import asyncio
-import os
-import sys
-
-import aiohttp
-from dotenv import load_dotenv
-from loguru import logger
-from runner import configure
-
-from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.pipeline.pipeline import Pipeline
-from pipecat.pipeline.runner import PipelineRunner
-from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
-from pipecat.services.cartesia import CartesiaTTSService
-from pipecat.services.fal import FalSTTService
-from pipecat.services.gladia import GladiaSTTService
-from pipecat.services.openai import OpenAILLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
-
-load_dotenv(override=True)
-
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
-
-
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
-
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-                vad_audio_passthrough=True,
-            ),
-        )
-
-        stt = FalSTTService(
-            api_key=os.getenv("FAL_KEY"),
-        )
-
-        tts = CartesiaTTSService(
-            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        )
-
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
-
-        messages = [
-            {
-                "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-            },
-        ]
-
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
-
-        pipeline = Pipeline(
-            [
-                transport.input(),  # Transport user input
-                stt,  # STT
-                context_aggregator.user(),  # User responses
-                llm,  # LLM
-                tts,  # TTS
-                transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
-            ]
-        )
-
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-                report_only_initial_ttfb=True,
-            ),
-        )
-
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
-            # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
-
-        # Register an event handler to exit the application when the user leaves.
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.cancel()
-
-        runner = PipelineRunner()
-
-        await runner.run(task)
-
-
-if __name__ == "__main__":
-    asyncio.run(main())
--- a/examples/foundational/07x-interruptible-local.py
+++ b/examples/foundational/07x-interruptible-local.py
@@ -1,91 +0,0 @@
-#
-# Copyright (c) 2024–2025, Daily
-#
-# SPDX-License-Identifier: BSD 2-Clause License
-#
-
-import asyncio
-import os
-import sys
-
-from dotenv import load_dotenv
-from loguru import logger
-
-from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.pipeline.pipeline import Pipeline
-from pipecat.pipeline.runner import PipelineRunner
-from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
-from pipecat.services.cartesia import CartesiaTTSService
-from pipecat.services.deepgram import DeepgramSTTService
-from pipecat.services.openai import OpenAILLMService
-from pipecat.transports.local.audio import LocalAudioTransport, LocalAudioTransportParams
-
-load_dotenv(override=True)
-
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
-
-
-async def main():
-    transport = LocalAudioTransport(
-        LocalAudioTransportParams(
-            audio_in_enabled=True,
-            audio_out_enabled=True,
-            vad_enabled=True,
-            vad_analyzer=SileroVADAnalyzer(),
-            vad_audio_passthrough=True,
-        )
-    )
-
-    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
-
-    tts = CartesiaTTSService(
-        api_key=os.getenv("CARTESIA_API_KEY"),
-        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-    )
-
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
-
-    messages = [
-        {
-            "role": "system",
-            "content": "You are a helpful LLM. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-        },
-    ]
-
-    context = OpenAILLMContext(messages)
-    context_aggregator = llm.create_context_aggregator(context)
-
-    pipeline = Pipeline(
-        [
-            transport.input(),  # Transport user input
-            stt,
-            context_aggregator.user(),  # User responses
-            llm,  # LLM
-            tts,  # TTS
-            transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
-        ]
-    )
-
-    task = PipelineTask(
-        pipeline,
-        params=PipelineParams(
-            allow_interruptions=True,
-            enable_metrics=True,
-            enable_usage_metrics=True,
-            report_only_initial_ttfb=True,
-        ),
-    )
-
-    messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-    await task.queue_frames([context_aggregator.user().get_context_frame()])
-
-    runner = PipelineRunner()
-
-    await runner.run(task)
-
-
-if __name__ == "__main__":
-    asyncio.run(main())
--- a/examples/foundational/10-wake-phrase.py
+++ b/examples/foundational/10-wake-phrase.py
@@ -47,7 +47,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
--- a/examples/foundational/11-sound-effects.py
+++ b/examples/foundational/11-sound-effects.py
@@ -100,7 +100,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        messages = [
--- a/examples/foundational/12-describe-video.py
+++ b/examples/foundational/12-describe-video.py
@@ -77,7 +77,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        @transport.event_handler("on_first_participant_joined")
--- a/examples/foundational/12a-describe-video-gemini-flash.py
+++ b/examples/foundational/12a-describe-video-gemini-flash.py
@@ -77,7 +77,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        @transport.event_handler("on_first_participant_joined")
--- a/examples/foundational/12b-describe-video-gpt-4o.py
+++ b/examples/foundational/12b-describe-video-gpt-4o.py
@@ -76,7 +76,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        @transport.event_handler("on_first_participant_joined")
--- a/examples/foundational/12c-describe-video-anthropic.py
+++ b/examples/foundational/12c-describe-video-anthropic.py
@@ -76,7 +76,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        @transport.event_handler("on_first_participant_joined")
--- a/examples/foundational/14-function-calling.py
+++ b/examples/foundational/14-function-calling.py
@@ -30,8 +30,13 @@ logger.remove(0)
 logger.add(sys.stderr, level="DEBUG")


-async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
+async def start_fetch_weather(function_name, llm, context):
+    """Push a frame to the LLM; this is handy when the LLM response might take a while."""
    await llm.push_frame(TTSSpeakFrame("Let me check on that."))
+    logger.debug(f"Starting fetch_weather_from_api with function_name: {function_name}")
+
+
+async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
    await result_callback({"conditions": "nice", "temperature": "75"})


@@ -53,14 +58,13 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
-
-        # You can also register a function_name of None to get all functions
+        # Register a function_name of None to get all functions
        # sent to the same callback with an additional function_name parameter.
-        llm.register_function("get_current_weather", fetch_weather_from_api)
+        llm.register_function(None, fetch_weather_from_api, start_callback=start_fetch_weather)

        weather_function = FunctionSchema(
            name="get_current_weather",
--- a/examples/foundational/14a-function-calling-anthropic.py
+++ b/examples/foundational/14a-function-calling-anthropic.py
@@ -53,11 +53,11 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        llm = AnthropicLLMService(
-            api_key=os.getenv("ANTHROPIC_API_KEY"), model="claude-3-7-sonnet-latest"
+            api_key=os.getenv("ANTHROPIC_API_KEY"), model="claude-3-5-sonnet-20240620"
        )
        llm.register_function("get_weather", get_weather)

--- a/examples/foundational/14b-function-calling-anthropic-video.py
+++ b/examples/foundational/14b-function-calling-anthropic-video.py
@@ -39,12 +39,7 @@ async def get_weather(function_name, tool_call_id, arguments, llm, context, resu

 async def get_image(function_name, tool_call_id, arguments, llm, context, result_callback):
    question = arguments["question"]
-    await llm.request_image_frame(
-        user_id=video_participant_id,
-        function_name=function_name,
-        tool_call_id=tool_call_id,
-        text_content=question,
-    )
+    await llm.request_image_frame(user_id=video_participant_id, text_content=question)


 async def main():
@@ -67,12 +62,13 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        llm = AnthropicLLMService(
            api_key=os.getenv("ANTHROPIC_API_KEY"),
-            model="claude-3-7-sonnet-latest",
+            # model="claude-3-5-sonnet-20240620",
+            model="claude-3-5-sonnet-latest",
            enable_prompt_caching_beta=True,
        )
        llm.register_function("get_weather", get_weather)
--- a/examples/foundational/14c-function-calling-together.py
+++ b/examples/foundational/14c-function-calling-together.py
@@ -31,8 +31,13 @@ logger.remove(0)
 logger.add(sys.stderr, level="DEBUG")


-async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
+async def start_fetch_weather(function_name, llm, context):
+    """Push a frame to the LLM; this is handy when the LLM response might take a while."""
    await llm.push_frame(TTSSpeakFrame("Let me check on that."))
+    logger.debug(f"Starting fetch_weather_from_api with function_name: {function_name}")
+
+
+async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
    await result_callback({"conditions": "nice", "temperature": "75"})


@@ -54,16 +59,16 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        llm = TogetherLLMService(
            api_key=os.getenv("TOGETHER_API_KEY"),
            model="meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
        )
-        # You can also register a function_name of None to get all functions
+        # Register a function_name of None to get all functions
        # sent to the same callback with an additional function_name parameter.
-        llm.register_function("get_current_weather", fetch_weather_from_api)
+        llm.register_function(None, fetch_weather_from_api, start_callback=start_fetch_weather)

        weather_function = FunctionSchema(
            name="get_current_weather",
--- a/examples/foundational/14d-function-calling-video.py
+++ b/examples/foundational/14d-function-calling-video.py
@@ -39,12 +39,7 @@ async def get_weather(function_name, tool_call_id, arguments, llm, context, resu
 async def get_image(function_name, tool_call_id, arguments, llm, context, result_callback):
    logger.debug(f"!!! IN get_image {video_participant_id}, {arguments}")
    question = arguments["question"]
-    await llm.request_image_frame(
-        user_id=video_participant_id,
-        function_name=function_name,
-        tool_call_id=tool_call_id,
-        text_content=question,
-    )
+    await llm.request_image_frame(user_id=video_participant_id, text_content=question)


 async def main():
@@ -65,7 +60,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
@@ -146,7 +141,7 @@ indicate you should use the get_image tool are:
            await transport.capture_participant_transcription(participant["id"])
            await transport.capture_participant_video(video_participant_id, framerate=0)
            # Kick off the conversation.
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+            await tts.say("Hi! Ask me about the weather in San Francisco.")

        runner = PipelineRunner()

--- a/examples/foundational/14e-function-calling-gemini.py
+++ b/examples/foundational/14e-function-calling-gemini.py
@@ -33,8 +33,13 @@ logger.add(sys.stderr, level="DEBUG")
 video_participant_id = None


-async def get_weather(function_name, tool_call_id, arguments, llm, context, result_callback):
+async def start_fetch_weather(function_name, llm, context):
+    """Push a frame to the LLM; this is handy when the LLM response might take a while."""
    await llm.push_frame(TTSSpeakFrame("Let me check on that."))
+    logger.debug(f"Starting fetch_weather_from_api with function_name: {function_name}")
+
+
+async def get_weather(function_name, tool_call_id, arguments, llm, context, result_callback):
    location = arguments["location"]
    await result_callback(f"The weather in {location} is currently 72 degrees and sunny.")

@@ -42,12 +47,7 @@ async def get_weather(function_name, tool_call_id, arguments, llm, context, resu
 async def get_image(function_name, tool_call_id, arguments, llm, context, result_callback):
    logger.debug(f"!!! IN get_image {video_participant_id}, {arguments}")
    question = arguments["question"]
-    await llm.request_image_frame(
-        user_id=video_participant_id,
-        function_name=function_name,
-        tool_call_id=tool_call_id,
-        text_content=question,
-    )
+    await llm.request_image_frame(user_id=video_participant_id, text_content=question)


 async def main():
@@ -68,11 +68,11 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"), model="gemini-2.0-flash-001")
-        llm.register_function("get_weather", get_weather)
+        llm.register_function("get_weather", get_weather, start_fetch_weather)
        llm.register_function("get_image", get_image)

        weather_function = FunctionSchema(
--- a/examples/foundational/14f-function-calling-groq.py
+++ b/examples/foundational/14f-function-calling-groq.py
@@ -31,8 +31,13 @@ logger.remove(0)
 logger.add(sys.stderr, level="DEBUG")


-async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
+async def start_fetch_weather(function_name, llm, context):
+    """Push a frame to the LLM; this is handy when the LLM response might take a while."""
    await llm.push_frame(TTSSpeakFrame("Let me check on that."))
+    logger.debug(f"Starting fetch_weather_from_api with function_name: {function_name}")
+
+
+async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
    await result_callback({"conditions": "nice", "temperature": "75"})


@@ -56,13 +61,13 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        llm = GroqLLMService(api_key=os.getenv("GROQ_API_KEY"), model="llama-3.3-70b-versatile")
-        # You can also register a function_name of None to get all functions
+        # Register a function_name of None to get all functions
        # sent to the same callback with an additional function_name parameter.
-        llm.register_function("get_current_weather", fetch_weather_from_api)
+        llm.register_function(None, fetch_weather_from_api, start_callback=start_fetch_weather)

        weather_function = FunctionSchema(
            name="get_current_weather",
--- a/examples/foundational/14g-function-calling-grok.py
+++ b/examples/foundational/14g-function-calling-grok.py
@@ -16,6 +16,7 @@ from runner import configure
 from pipecat.adapters.schemas.function_schema import FunctionSchema
 from pipecat.adapters.schemas.tools_schema import ToolsSchema
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import TTSSpeakFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -30,6 +31,12 @@ logger.remove(0)
 logger.add(sys.stderr, level="DEBUG")


+async def start_fetch_weather(function_name, llm, context):
+    """Push a frame to the LLM; this is handy when the LLM response might take a while."""
+    await llm.push_frame(TTSSpeakFrame("Let me check on that."))
+    logger.debug(f"Starting fetch_weather_from_api with function_name: {function_name}")
+
+
 async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
    await result_callback({"conditions": "nice", "temperature": "75"})

@@ -52,13 +59,13 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        llm = GrokLLMService(api_key=os.getenv("GROK_API_KEY"))
-        # You can also register a function_name of None to get all functions
+        # Register a function_name of None to get all functions
        # sent to the same callback with an additional function_name parameter.
-        llm.register_function("get_current_weather", fetch_weather_from_api)
+        llm.register_function(None, fetch_weather_from_api, start_callback=start_fetch_weather)

        weather_function = FunctionSchema(
            name="get_current_weather",
--- a/examples/foundational/14h-function-calling-azure.py
+++ b/examples/foundational/14h-function-calling-azure.py
@@ -31,8 +31,13 @@ logger.remove(0)
 logger.add(sys.stderr, level="DEBUG")


-async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
+async def start_fetch_weather(function_name, llm, context):
+    """Push a frame to the LLM; this is handy when the LLM response might take a while."""
    await llm.push_frame(TTSSpeakFrame("Let me check on that."))
+    logger.debug(f"Starting fetch_weather_from_api with function_name: {function_name}")
+
+
+async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
    await result_callback({"conditions": "nice", "temperature": "75"})


@@ -54,7 +59,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        llm = AzureLLMService(
@@ -62,9 +67,9 @@ async def main():
            endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
            model=os.getenv("AZURE_CHATGPT_MODEL"),
        )
-        # You can also register a function_name of None to get all functions
+        # Register a function_name of None to get all functions
        # sent to the same callback with an additional function_name parameter.
-        llm.register_function("get_current_weather", fetch_weather_from_api)
+        llm.register_function(None, fetch_weather_from_api, start_callback=start_fetch_weather)

        weather_function = FunctionSchema(
            name="get_current_weather",
--- a/examples/foundational/14i-function-calling-fireworks.py
+++ b/examples/foundational/14i-function-calling-fireworks.py
@@ -31,8 +31,13 @@ logger.remove(0)
 logger.add(sys.stderr, level="DEBUG")


-async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
+async def start_fetch_weather(function_name, llm, context):
+    """Push a frame to the LLM; this is handy when the LLM response might take a while."""
    await llm.push_frame(TTSSpeakFrame("Let me check on that."))
+    logger.debug(f"Starting fetch_weather_from_api with function_name: {function_name}")
+
+
+async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
    await result_callback({"conditions": "nice", "temperature": "75"})


@@ -54,16 +59,16 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        llm = FireworksLLMService(
            api_key=os.getenv("FIREWORKS_API_KEY"),
-            model="accounts/fireworks/models/llama-v3p1-405b-instruct",
+            model="accounts/fireworks/models/firefunction-v2",
        )
-        # You can also register a function_name of None to get all functions
+        # Register a function_name of None to get all functions
        # sent to the same callback with an additional function_name parameter.
-        llm.register_function("get_current_weather", fetch_weather_from_api)
+        llm.register_function(None, fetch_weather_from_api, start_callback=start_fetch_weather)

        weather_function = FunctionSchema(
            name="get_current_weather",
--- a/examples/foundational/14j-function-calling-nim.py
+++ b/examples/foundational/14j-function-calling-nim.py
@@ -31,8 +31,13 @@ logger.remove(0)
 logger.add(sys.stderr, level="DEBUG")


-async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
+async def start_fetch_weather(function_name, llm, context):
+    """Push a frame to the LLM; this is handy when the LLM response might take a while."""
    await llm.push_frame(TTSSpeakFrame("Let me check on that."))
+    logger.debug(f"Starting fetch_weather_from_api with function_name: {function_name}")
+
+
+async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
    await result_callback({"conditions": "nice", "temperature": "75"})


@@ -54,16 +59,16 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-            # text_filters=[MarkdownTextFilter()],
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
+            # text_filter=MarkdownTextFilter(),
        )

        llm = NimLLMService(
            api_key=os.getenv("NVIDIA_API_KEY"), model="meta/llama-3.3-70b-instruct"
        )
-        # You can also register a function_name of None to get all functions
+        # Register a function_name of None to get all functions
        # sent to the same callback with an additional function_name parameter.
-        llm.register_function("get_current_weather", fetch_weather_from_api)
+        llm.register_function(None, fetch_weather_from_api, start_callback=start_fetch_weather)

        weather_function = FunctionSchema(
            name="get_current_weather",
--- a/examples/foundational/14k-function-calling-cerebras.py
+++ b/examples/foundational/14k-function-calling-cerebras.py
@@ -31,8 +31,13 @@ logger.remove(0)
 logger.add(sys.stderr, level="DEBUG")


-async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
+async def start_fetch_weather(function_name, llm, context):
+    """Push a frame to the LLM; this is handy when the LLM response might take a while."""
    await llm.push_frame(TTSSpeakFrame("Let me check on that."))
+    logger.debug(f"Starting fetch_weather_from_api with function_name: {function_name}")
+
+
+async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
    await result_callback({"conditions": "nice", "temperature": "75"})


@@ -54,13 +59,13 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        llm = CerebrasLLMService(api_key=os.getenv("CEREBRAS_API_KEY"), model="llama-3.3-70b")
-        # You can also register a function_name of None to get all functions
+        # Register a function_name of None to get all functions
        # sent to the same callback with an additional function_name parameter.
-        llm.register_function("get_current_weather", fetch_weather_from_api)
+        llm.register_function(None, fetch_weather_from_api, start_callback=start_fetch_weather)

        weather_function = FunctionSchema(
            name="get_current_weather",
--- a/examples/foundational/14l-function-calling-deepseek.py
+++ b/examples/foundational/14l-function-calling-deepseek.py
@@ -31,8 +31,13 @@ logger.remove(0)
 logger.add(sys.stderr, level="DEBUG")


-async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
+async def start_fetch_weather(function_name, llm, context):
+    """Push a frame to the LLM; this is handy when the LLM response might take a while."""
    await llm.push_frame(TTSSpeakFrame("Let me check on that."))
+    logger.debug(f"Starting fetch_weather_from_api with function_name: {function_name}")
+
+
+async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
    await result_callback({"conditions": "nice", "temperature": "75"})


@@ -54,13 +59,13 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        llm = DeepSeekLLMService(api_key=os.getenv("DEEPSEEK_API_KEY"), model="deepseek-chat")
-        # You can also register a function_name of None to get all functions
+        # Register a function_name of None to get all functions
        # sent to the same callback with an additional function_name parameter.
-        llm.register_function("get_current_weather", fetch_weather_from_api)
+        llm.register_function(None, fetch_weather_from_api, start_callback=start_fetch_weather)

        weather_function = FunctionSchema(
            name="get_current_weather",
--- a/examples/foundational/14m-function-calling-openrouter.py
+++ b/examples/foundational/14m-function-calling-openrouter.py
@@ -31,8 +31,13 @@ logger.remove(0)
 logger.add(sys.stderr, level="DEBUG")


-async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
+async def start_fetch_weather(function_name, llm, context):
+    """Push a frame to the LLM; this is handy when the LLM response might take a while."""
    await llm.push_frame(TTSSpeakFrame("Let me check on that."))
+    logger.debug(f"Starting fetch_weather_from_api with function_name: {function_name}")
+
+
+async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
    await result_callback({"conditions": "nice", "temperature": "75"})


@@ -62,9 +67,9 @@ async def main():
        llm = OpenRouterLLMService(
            api_key=os.getenv("OPENROUTER_API_KEY"), model="openai/gpt-4o-2024-11-20"
        )
-        # You can also register a function_name of None to get all functions
+        # Register a function_name of None to get all functions
        # sent to the same callback with an additional function_name parameter.
-        llm.register_function("get_current_weather", fetch_weather_from_api)
+        llm.register_function(None, fetch_weather_from_api, start_callback=start_fetch_weather)

        weather_function = FunctionSchema(
            name="get_current_weather",
--- a/examples/foundational/14n-function-calling-perplexity.py
+++ b/examples/foundational/14n-function-calling-perplexity.py
@@ -55,7 +55,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        llm = PerplexityLLMService(api_key=os.getenv("PERPLEXITY_API_KEY"), model="sonar")
--- a/examples/foundational/14o-function-calling-gemini-openai-format.py
+++ b/examples/foundational/14o-function-calling-gemini-openai-format.py
@@ -31,8 +31,13 @@ logger.remove(0)
 logger.add(sys.stderr, level="DEBUG")


-async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
+async def start_fetch_weather(function_name, llm, context):
+    """Push a frame to the LLM; this is handy when the LLM response might take a while."""
    await llm.push_frame(TTSSpeakFrame("Let me check on that."))
+    logger.debug(f"Starting fetch_weather_from_api with function_name: {function_name}")
+
+
+async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
    await result_callback({"conditions": "nice", "temperature": "75"})


@@ -58,9 +63,11 @@ async def main():
        )

        llm = GoogleLLMOpenAIBetaService(api_key=os.getenv("GEMINI_API_KEY"))
-        # You can aslo register a function_name of None to get all functions
+        # Register a function_name of None to get all functions
        # sent to the same callback with an additional function_name parameter.
-        llm.register_function("get_current_weather", fetch_weather_from_api)
+        llm.register_function(
+            "get_current_weather", fetch_weather_from_api, start_callback=start_fetch_weather
+        )

        weather_function = FunctionSchema(
            name="get_current_weather",
--- a/examples/foundational/14p-function-calling-gemini-vertex-ai.py
+++ b/examples/foundational/14p-function-calling-gemini-vertex-ai.py
@@ -1,130 +0,0 @@
-#
-# Copyright (c) 2024–2025, Daily
-#
-# SPDX-License-Identifier: BSD 2-Clause License
-#
-
-import asyncio
-import os
-import sys
-
-import aiohttp
-from dotenv import load_dotenv
-from loguru import logger
-from runner import configure
-
-from pipecat.adapters.schemas.function_schema import FunctionSchema
-from pipecat.adapters.schemas.tools_schema import ToolsSchema
-from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import TTSSpeakFrame
-from pipecat.pipeline.pipeline import Pipeline
-from pipecat.pipeline.runner import PipelineRunner
-from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.services.elevenlabs import ElevenLabsTTSService
-from pipecat.services.google import GoogleVertexLLMService
-from pipecat.services.openai import OpenAILLMContext
-from pipecat.transports.services.daily import DailyParams, DailyTransport
-
-load_dotenv(override=True)
-
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
-
-
-async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
-    await llm.push_frame(TTSSpeakFrame("Let me check on that."))
-    await result_callback({"conditions": "nice", "temperature": "75"})
-
-
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
-
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                transcription_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-            ),
-        )
-
-        tts = ElevenLabsTTSService(
-            api_key=os.getenv("ELEVENLABS_API_KEY", ""),
-            voice_id=os.getenv("ELEVENLABS_VOICE_ID", ""),
-        )
-
-        llm = GoogleVertexLLMService(
-            # credentials="<json-credentials>",
-            params=GoogleVertexLLMService.InputParams(
-                project_id="<google-project-id>",
-            )
-        )
-        # You can aslo register a function_name of None to get all functions
-        # sent to the same callback with an additional function_name parameter.
-        llm.register_function("get_current_weather", fetch_weather_from_api)
-
-        weather_function = FunctionSchema(
-            name="get_current_weather",
-            description="Get the current weather",
-            properties={
-                "location": {
-                    "type": "string",
-                    "description": "The city and state, e.g. San Francisco, CA",
-                },
-                "format": {
-                    "type": "string",
-                    "enum": ["celsius", "fahrenheit"],
-                    "description": "The temperature unit to use. Infer this from the user's location.",
-                },
-            },
-            required=["location", "format"],
-        )
-        tools = ToolsSchema(standard_tools=[weather_function])
-
-        messages = [
-            {
-                "role": "user",
-                "content": "Start a conversation with 'Hey there' to get the current weather.",
-            },
-        ]
-
-        context = OpenAILLMContext(messages, tools)
-        context_aggregator = llm.create_context_aggregator(context)
-
-        pipeline = Pipeline(
-            [
-                transport.input(),
-                context_aggregator.user(),
-                llm,
-                tts,
-                transport.output(),
-                context_aggregator.assistant(),
-            ]
-        )
-
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-            ),
-        )
-
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
-            # Kick off the conversation.
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
-
-        runner = PipelineRunner()
-
-        await runner.run(task)
-
-
-if __name__ == "__main__":
-    asyncio.run(main())
--- a/examples/foundational/15-switch-voices.py
+++ b/examples/foundational/15-switch-voices.py
@@ -78,7 +78,7 @@ async def main():

        british_lady = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        barbershop_man = CartesiaTTSService(
@@ -125,10 +125,7 @@ async def main():
                llm,  # LLM
                ParallelPipeline(  # TTS (one of the following vocies)
                    [FunctionFilter(news_lady_filter), news_lady],  # News Lady voice
-                    [
-                        FunctionFilter(british_lady_filter),
-                        british_lady,
-                    ],  # British Reading Lady voice
+                    [FunctionFilter(british_lady_filter), british_lady],  # British Lady voice
                    [FunctionFilter(barbershop_man_filter), barbershop_man],  # Barbershop Man voice
                ),
                transport.output(),  # Transport bot output
--- a/examples/foundational/15a-switch-languages.py
+++ b/examples/foundational/15a-switch-languages.py
@@ -71,7 +71,7 @@ async def main():

        english_tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        spanish_tts = CartesiaTTSService(
--- a/examples/foundational/17-detect-user-idle.py
+++ b/examples/foundational/17-detect-user-idle.py
@@ -48,7 +48,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
--- a/examples/foundational/19-openai-realtime-beta.py
+++ b/examples/foundational/19-openai-realtime-beta.py
@@ -14,8 +14,6 @@ from dotenv import load_dotenv
 from loguru import logger
 from runner import configure

-from pipecat.adapters.schemas.function_schema import FunctionSchema
-from pipecat.adapters.schemas.tools_schema import ToolsSchema
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.pipeline.pipeline import Pipeline
@@ -23,11 +21,10 @@ from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.openai_realtime_beta import (
-    InputAudioNoiseReduction,
    InputAudioTranscription,
    OpenAIRealtimeBetaLLMService,
-    SemanticTurnDetection,
    SessionProperties,
+    TurnDetection,
 )
 from pipecat.transports.services.daily import DailyParams, DailyTransport

@@ -49,25 +46,28 @@ async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context
    )


-weather_function = FunctionSchema(
-    name="get_current_weather",
-    description="Get the current weather",
-    properties={
-        "location": {
-            "type": "string",
-            "description": "The city and state, e.g. San Francisco, CA",
+tools = [
+    {
+        "type": "function",
+        "name": "get_current_weather",
+        "description": "Get the current weather",
+        "parameters": {
+            "type": "object",
+            "properties": {
+                "location": {
+                    "type": "string",
+                    "description": "The city and state, e.g. San Francisco, CA",
+                },
+                "format": {
+                    "type": "string",
+                    "enum": ["celsius", "fahrenheit"],
+                    "description": "The temperature unit to use. Infer this from the users location.",
+                },
+            },
+            "required": ["location", "format"],
        },
-        "format": {
-            "type": "string",
-            "enum": ["celsius", "fahrenheit"],
-            "description": "The temperature unit to use. Infer this from the users location.",
-        },
-    },
-    required=["location", "format"],
-)
-
-# Create tools schema
-tools = ToolsSchema(standard_tools=[weather_function])
+    }
+]


 async def main():
@@ -92,10 +92,9 @@ async def main():
            input_audio_transcription=InputAudioTranscription(),
            # Set openai TurnDetection parameters. Not setting this at all will turn it
            # on by default
-            turn_detection=SemanticTurnDetection(),
+            turn_detection=TurnDetection(silence_duration_ms=1000),
            # Or set to False to disable openai turn detection and use transport VAD
            # turn_detection=False,
-            input_audio_noise_reduction=InputAudioNoiseReduction(type="near_field"),
            # tools=tools,
            instructions="""Your knowledge cutoff is 2023-10. You are a helpful and friendly AI.

@@ -148,8 +147,8 @@ Remember, your responses should be short. Just one or two sentences, usually."""
                transport.input(),  # Transport user input
                context_aggregator.user(),
                llm,  # LLM
-                transport.output(),  # Transport bot output
                context_aggregator.assistant(),
+                transport.output(),  # Transport bot output
            ]
        )

--- a/examples/foundational/19a-azure-realtime-beta.py
+++ b/examples/foundational/19a-azure-realtime-beta.py
@@ -10,12 +10,11 @@ import sys
 from datetime import datetime

 import aiohttp
+import websockets
 from dotenv import load_dotenv
 from loguru import logger
 from runner import configure

-from pipecat.adapters.schemas.function_schema import FunctionSchema
-from pipecat.adapters.schemas.tools_schema import ToolsSchema
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.pipeline.pipeline import Pipeline
@@ -26,6 +25,7 @@ from pipecat.services.openai_realtime_beta import (
    AzureRealtimeBetaLLMService,
    InputAudioTranscription,
    SessionProperties,
+    TurnDetection,
 )
 from pipecat.transports.services.daily import DailyParams, DailyTransport

@@ -47,26 +47,28 @@ async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context
    )


-# Define weather function using standardized schema
-weather_function = FunctionSchema(
-    name="get_current_weather",
-    description="Get the current weather",
-    properties={
-        "location": {
-            "type": "string",
-            "description": "The city and state, e.g. San Francisco, CA",
+tools = [
+    {
+        "type": "function",
+        "name": "get_current_weather",
+        "description": "Get the current weather",
+        "parameters": {
+            "type": "object",
+            "properties": {
+                "location": {
+                    "type": "string",
+                    "description": "The city and state, e.g. San Francisco, CA",
+                },
+                "format": {
+                    "type": "string",
+                    "enum": ["celsius", "fahrenheit"],
+                    "description": "The temperature unit to use. Infer this from the users location.",
+                },
+            },
+            "required": ["location", "format"],
        },
-        "format": {
-            "type": "string",
-            "enum": ["celsius", "fahrenheit"],
-            "description": "The temperature unit to use. Infer this from the users location.",
-        },
-    },
-    required=["location", "format"],
-)
-
-# Create tools schema
-tools = ToolsSchema(standard_tools=[weather_function])
+    }
+]


 async def main():
--- a/examples/foundational/20a-persistent-context-openai.py
+++ b/examples/foundational/20a-persistent-context-openai.py
@@ -184,7 +184,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
--- a/examples/foundational/20c-persistent-context-anthropic.py
+++ b/examples/foundational/20c-persistent-context-anthropic.py
@@ -179,7 +179,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        llm = AnthropicLLMService(
--- a/examples/foundational/20d-persistent-context-gemini.py
+++ b/examples/foundational/20d-persistent-context-gemini.py
@@ -54,12 +54,7 @@ async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context

 async def get_image(function_name, tool_call_id, arguments, llm, context, result_callback):
    question = arguments["question"]
-    await llm.request_image_frame(
-        user_id=video_participant_id,
-        function_name=function_name,
-        tool_call_id=tool_call_id,
-        text_content=question,
-    )
+    await llm.request_image_frame(user_id=video_participant_id, text_content=question)


 async def get_saved_conversation_filenames(
@@ -239,7 +234,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        llm = GoogleLLMService(model="gemini-2.0-flash-001", api_key=os.getenv("GOOGLE_API_KEY"))
--- a/examples/foundational/22-natural-conversation.py
+++ b/examples/foundational/22-natural-conversation.py
@@ -56,7 +56,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        # This is the LLM that will be used to detect if the user has finished a
--- a/examples/foundational/22b-natural-conversation-proposal.py
+++ b/examples/foundational/22b-natural-conversation-proposal.py
@@ -199,8 +199,13 @@ class OutputGate(FrameProcessor):
                break


-async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
+async def start_fetch_weather(function_name, llm, context):
+    """Push a frame to the LLM; this is handy when the LLM response might take a while."""
    await llm.push_frame(TTSSpeakFrame("Let me check on that."))
+    logger.debug(f"Starting fetch_weather_from_api with function_name: {function_name}")
+
+
+async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
    await result_callback({"conditions": "nice", "temperature": "75"})


@@ -224,7 +229,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        # This is the LLM that will be used to detect if the user has finished a
@@ -234,9 +239,9 @@ async def main():

        # This is the regular LLM.
        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
-        # You can also register a function_name of None to get all functions
+        # Register a function_name of None to get all functions
        # sent to the same callback with an additional function_name parameter.
-        llm.register_function("get_current_weather", fetch_weather_from_api)
+        llm.register_function(None, fetch_weather_from_api, start_callback=start_fetch_weather)

        tools = [
            ChatCompletionToolParam(
--- a/examples/foundational/22c-natural-conversation-mixed-llms.py
+++ b/examples/foundational/22c-natural-conversation-mixed-llms.py
@@ -403,8 +403,13 @@ class OutputGate(FrameProcessor):
                break


-async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
+async def start_fetch_weather(function_name, llm, context):
+    """Push a frame to the LLM; this is handy when the LLM response might take a while."""
    await llm.push_frame(TTSSpeakFrame("Let me check on that."))
+    logger.debug(f"Starting fetch_weather_from_api with function_name: {function_name}")
+
+
+async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
    await result_callback({"conditions": "nice", "temperature": "75"})


@@ -428,7 +433,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        # This is the LLM that will be used to detect if the user has finished a
@@ -446,7 +451,7 @@ async def main():
        )
        # Register a function_name of None to get all functions
        # sent to the same callback with an additional function_name parameter.
-        llm.register_function("get_current_weather", fetch_weather_from_api)
+        llm.register_function(None, fetch_weather_from_api, start_callback=start_fetch_weather)

        tools = [
            ChatCompletionToolParam(
--- a/examples/foundational/22d-natural-conversation-gemini-audio.py
+++ b/examples/foundational/22d-natural-conversation-gemini-audio.py
@@ -644,7 +644,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        # This is the LLM that will transcribe user speech.
--- a/examples/foundational/23-bot-background-sound.py
+++ b/examples/foundational/23-bot-background-sound.py
@@ -59,7 +59,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
--- a/examples/foundational/24-stt-mute-filter.py
+++ b/examples/foundational/24-stt-mute-filter.py
@@ -30,6 +30,10 @@ logger.remove(0)
 logger.add(sys.stderr, level="DEBUG")


+async def start_fetch_weather(function_name, llm, context):
+    logger.debug(f"Starting fetch_weather_from_api with function_name: {function_name}")
+
+
 async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
    # Add a delay to test interruption during function calls
    logger.info("Weather API call starting...")
@@ -68,7 +72,7 @@ async def main():
        tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-helios-en")

        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
-        llm.register_function("get_current_weather", fetch_weather_from_api)
+        llm.register_function(None, fetch_weather_from_api, start_callback=start_fetch_weather)

        tools = [
            ChatCompletionToolParam(
--- a/examples/foundational/25-google-audio-in.py
+++ b/examples/foundational/25-google-audio-in.py
@@ -294,7 +294,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        conversation_llm = GoogleLLMService(
--- a/examples/foundational/26-gemini-multimodal-live.py
+++ b/examples/foundational/26-gemini-multimodal-live.py
@@ -77,7 +77,7 @@ async def main():
                    LLMMessagesAppendFrame(
                        messages=[
                            {
-                                "role": "user",
+                                "role": "assistant",
                                "content": "Greet the user.",
                            }
                        ]
--- a/examples/foundational/26d-gemini-multimodal-live-text.py
+++ b/examples/foundational/26d-gemini-multimodal-live-text.py
@@ -78,7 +78,7 @@ async def main():
        # )

        tts = CartesiaTTSService(
-            api_key=os.getenv("CARTESIA_API_KEY"), voice_id="71a7ad14-091c-4e8e-a314-022ece01c121"
+            api_key=os.getenv("CARTESIA_API_KEY"), voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22"
        )

        messages = [
--- a/examples/foundational/28a-transcription-processor-openai.py
+++ b/examples/foundational/28a-transcription-processor-openai.py
@@ -113,7 +113,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        llm = OpenAILLMService(
--- a/examples/foundational/28b-transcript-processor-anthropic.py
+++ b/examples/foundational/28b-transcript-processor-anthropic.py
@@ -0,0 +1,177 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import os
+import sys
+from typing import List, Optional
+
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import TranscriptionMessage, TranscriptionUpdateFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.processors.transcript_processor import TranscriptProcessor
+from pipecat.services.anthropic import AnthropicLLMService
+from pipecat.services.cartesia import CartesiaTTSService
+from pipecat.services.deepgram import DeepgramSTTService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+class TranscriptHandler:
+    """Handles real-time transcript processing and output.
+
+    Maintains a list of conversation messages and outputs them either to a log
+    or to a file as they are received. Each message includes its timestamp and role.
+
+    Attributes:
+        messages: List of all processed transcript messages
+        output_file: Optional path to file where transcript is saved. If None, outputs to log only.
+    """
+
+    def __init__(self, output_file: Optional[str] = None):
+        """Initialize handler with optional file output.
+
+        Args:
+            output_file: Path to output file. If None, outputs to log only.
+        """
+        self.messages: List[TranscriptionMessage] = []
+        self.output_file: Optional[str] = output_file
+        logger.debug(
+            f"TranscriptHandler initialized {'with output_file=' + output_file if output_file else 'with log output only'}"
+        )
+
+    async def save_message(self, message: TranscriptionMessage):
+        """Save a single transcript message.
+
+        Outputs the message to the log and optionally to a file.
+
+        Args:
+            message: The message to save
+        """
+        timestamp = f"[{message.timestamp}] " if message.timestamp else ""
+        line = f"{timestamp}{message.role}: {message.content}"
+
+        # Always log the message
+        logger.info(f"Transcript: {line}")
+
+        # Optionally write to file
+        if self.output_file:
+            try:
+                with open(self.output_file, "a", encoding="utf-8") as f:
+                    f.write(line + "\n")
+            except Exception as e:
+                logger.error(f"Error saving transcript message to file: {e}")
+
+    async def on_transcript_update(
+        self, processor: TranscriptProcessor, frame: TranscriptionUpdateFrame
+    ):
+        """Handle new transcript messages.
+
+        Args:
+            processor: The TranscriptProcessor that emitted the update
+            frame: TranscriptionUpdateFrame containing new messages
+        """
+        logger.debug(f"Received transcript update with {len(frame.messages)} new messages")
+
+        for msg in frame.messages:
+            self.messages.append(msg)
+            await self.save_message(msg)
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, token) = await configure(session)
+
+        transport = DailyTransport(
+            room_url,
+            None,
+            "Respond bot",
+            DailyParams(
+                audio_out_enabled=True,
+                vad_enabled=True,
+                vad_analyzer=SileroVADAnalyzer(),
+                vad_audio_passthrough=True,
+            ),
+        )
+
+        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+        tts = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
+        )
+
+        llm = AnthropicLLMService(
+            api_key=os.getenv("ANTHROPIC_API_KEY"), model="claude-3-5-sonnet-20241022"
+        )
+
+        messages = [
+            {
+                "role": "system",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative, helpful, and brief way.",
+            },
+            {"role": "user", "content": "Say hello."},
+        ]
+
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
+
+        # Create transcript processor and handler
+        transcript = TranscriptProcessor()
+        transcript_handler = TranscriptHandler()  # Output to log only
+        # transcript_handler = TranscriptHandler(output_file="transcript.txt") # Output to file and log
+
+        pipeline = Pipeline(
+            [
+                transport.input(),  # Transport user input
+                stt,  # STT
+                transcript.user(),  # User transcripts
+                context_aggregator.user(),  # User responses
+                llm,  # LLM
+                tts,  # TTS
+                transport.output(),  # Transport bot output
+                transcript.assistant(),  # Assistant transcripts
+                context_aggregator.assistant(),  # Assistant spoken responses
+            ]
+        )
+
+        task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            await transport.capture_participant_transcription(participant["id"])
+            # Kick off the conversation.
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        # Register event handler for transcript updates
+        @transcript.event_handler("on_transcript_update")
+        async def on_transcript_update(processor, frame):
+            await transcript_handler.on_transcript_update(processor, frame)
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            # Stop the pipeline immediately when the participant leaves
+            await task.cancel()
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())
--- a/examples/foundational/28c-transcription-processor-gemini.py
+++ b/examples/foundational/28c-transcription-processor-gemini.py
@@ -0,0 +1,210 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import os
+import sqlite3
+import sys
+from typing import List, Optional
+
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import TranscriptionMessage, TranscriptionUpdateFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.processors.transcript_processor import TranscriptProcessor
+from pipecat.services.cartesia import CartesiaTTSService
+from pipecat.services.deepgram import DeepgramSTTService
+from pipecat.services.google import GoogleLLMService
+from pipecat.services.openai import OpenAILLMContext
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+class TranscriptHandler:
+    """Handles real-time transcript processing and output.
+
+    Maintains a list of conversation messages and outputs them either to a log
+    or to a file as they are received. Each message includes its timestamp and role.
+
+    Attributes:
+        messages: List of all processed transcript messages
+        output_file: Optional path to file where transcript is saved. If None, outputs to log only.
+    """
+
+    def __init__(self, output_file: Optional[str] = None, output_db: Optional[str] = None):
+        """Initialize handler with optional file or database output.
+
+        Args:
+            output_file: Path to output file. If None, outputs to log only.
+        """
+        self.messages: List[TranscriptionMessage] = []
+        self.output_file: Optional[str] = output_file
+        self.output_db: Optional[str] = output_db
+
+        if self.output_db:
+            self.con = sqlite3.connect("example.db")
+            self.db = self.con.cursor()
+
+            table = self.db.execute("SELECT name FROM sqlite_master WHERE name='messages'")
+            if not (table.fetchone()):
+                self.db.execute(
+                    "CREATE TABLE messages(role TEXT, content TEXT, timestamp DATETIME DEFAULT CURRENT_TIMESTAMP )"
+                )
+        logger.debug(
+            f"TranscriptHandler initialized; output file: {output_file}, output DB: {output_db}"
+        )
+
+    async def save_message(self, message: TranscriptionMessage):
+        """Save a single transcript message.
+
+        Outputs the message to the log and optionally to a SQLite database or file.
+
+        Args:
+            message: The message to save
+        """
+        timestamp = f"[{message.timestamp}] " if message.timestamp else ""
+        line = f"{timestamp}{message.role}: {message.content}"
+
+        # Always log the message
+        logger.info(f"Transcript: {line}")
+
+        # Optionally write to file
+        if self.output_file:
+            try:
+                with open(self.output_file, "a", encoding="utf-8") as f:
+                    f.write(line + "\n")
+            except Exception as e:
+                logger.error(f"Error saving transcript message to file: {e}")
+
+        # and/or to a SQLite database
+        if self.output_db:
+            self.db.execute(
+                "INSERT INTO messages VALUES (?, ?, ?)",
+                (message.role, message.content, message.timestamp),
+            )
+            self.con.commit()
+
+    async def on_transcript_update(
+        self, processor: TranscriptProcessor, frame: TranscriptionUpdateFrame
+    ):
+        """Handle new transcript messages.
+
+        Args:
+            processor: The TranscriptProcessor that emitted the update
+            frame: TranscriptionUpdateFrame containing new messages
+        """
+        logger.debug(f"Received transcript update with {len(frame.messages)} new messages")
+
+        for msg in frame.messages:
+            self.messages.append(msg)
+            await self.save_message(msg)
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, token) = await configure(session)
+
+        transport = DailyTransport(
+            room_url,
+            None,
+            "Respond bot",
+            DailyParams(
+                audio_out_enabled=True,
+                vad_enabled=True,
+                vad_analyzer=SileroVADAnalyzer(),
+                vad_audio_passthrough=True,
+            ),
+        )
+
+        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+        tts = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
+        )
+
+        llm = GoogleLLMService(
+            model="models/gemini-2.0-flash-exp",
+            # model="gemini-exp-1114",
+            api_key=os.getenv("GOOGLE_API_KEY"),
+        )
+
+        messages = [
+            {
+                "role": "system",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative, helpful, and brief way.",
+            },
+            {"role": "user", "content": "Say hello."},
+        ]
+
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
+
+        # Create transcript processor and handler
+        transcript = TranscriptProcessor()
+        # Select a TranscriptHandler output method
+        # Uncomment out only one of the following lines:
+        transcript_handler = TranscriptHandler()  # Output to log only
+        # transcript_handler = TranscriptHandler(output_file="transcript.txt") # Output to file and log
+        # transcript_handler = TranscriptHandler(output_db="example.db")  # Output to SQLite DB and log
+
+        pipeline = Pipeline(
+            [
+                transport.input(),  # Transport user input
+                stt,  # STT
+                transcript.user(),  # User transcripts
+                context_aggregator.user(),  # User responses
+                llm,  # LLM
+                tts,  # TTS
+                transport.output(),  # Transport bot output
+                transcript.assistant(),  # Assistant transcripts
+                context_aggregator.assistant(),  # Assistant spoken responses
+            ]
+        )
+
+        task = PipelineTask(
+            pipeline,
+            params=PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=True,
+            ),
+        )
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            await transport.capture_participant_transcription(participant["id"])
+            # Kick off the conversation.
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        # Register event handler for transcript updates
+        @transcript.event_handler("on_transcript_update")
+        async def on_transcript_update(processor, frame):
+            await transcript_handler.on_transcript_update(processor, frame)
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            # Stop the pipeline immediately when the participant leaves
+            await task.cancel()
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())
--- a/examples/foundational/29-livekit-audio-chat.py
+++ b/examples/foundational/29-livekit-audio-chat.py
@@ -131,7 +131,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        messages = [
--- a/examples/foundational/30-observer.py
+++ b/examples/foundational/30-observer.py
@@ -89,7 +89,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
--- a/examples/foundational/32-gemini-grounding-metadata.py
+++ b/examples/foundational/32-gemini-grounding-metadata.py
@@ -81,7 +81,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        # Initialize the Gemini Multimodal Live model
--- a/examples/foundational/34-audio-recording.py
+++ b/examples/foundational/34-audio-recording.py
@@ -32,7 +32,6 @@ Requirements:
        OPENAI_API_KEY=your_openai_key
        CARTESIA_API_KEY=your_cartesia_key
        DAILY_API_KEY=your_daily_key
-        DEEPGRAM_API_KEY=your_deepgram_key

 The recordings will be saved in a 'recordings' directory with timestamps:
    recordings/
@@ -66,7 +65,6 @@ from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.processors.audio.audio_buffer_processor import AudioBufferProcessor
 from pipecat.services.cartesia import CartesiaTTSService
-from pipecat.services.deepgram import DeepgramSTTService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport

@@ -100,17 +98,16 @@ async def main():
            DailyParams(
                # audio_in_enabled=True,
                audio_out_enabled=True,
+                transcription_enabled=True,
                vad_enabled=True,
                vad_analyzer=SileroVADAnalyzer(),
-                vad_audio_passthrough=True,
+                vad_audio_passthrough=True,  # Enable audio passthrough for recording
            ),
        )

-        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"), audio_passthrough=True)
-
        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",
        )

        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4")
@@ -131,7 +128,6 @@ async def main():
        pipeline = Pipeline(
            [
                transport.input(),
-                stt,
                context_aggregator.user(),
                llm,
                tts,
--- a/examples/foundational/35-mem0.py
+++ b/examples/foundational/35-mem0.py
@@ -1,242 +0,0 @@
-#
-# Copyright (c) 2024–2025, Daily
-#
-# SPDX-License-Identifier: BSD 2-Clause License
-#
-
-"""Mem0 Personalized Voice Agent Example with Pipecat.
-
-This example demonstrates how to create a conversational AI assistant with memory capabilities
-using Mem0 integration. It shows how to build an agent that remembers previous interactions
-and personalizes responses based on conversation history.
-
-The example:
-    1. Sets up a video/audio conversation between a user and an AI assistant
-    2. Uses Mem0 to store and retrieve memories from conversations
-    3. Creates personalized greetings based on previous interactions
-    4. Handles multi-modal interaction through audio
-
-Example usage (run from pipecat root directory):
-    $ pip install "pipecat-ai[daily,openai,elevenlabs,silero,mem0]"
-    $ python examples/foundational/35-mem0.py
-
-Requirements:
-    - OpenAI API key (for GPT-4o-mini)
-    - ElevenLabs API key (for text-to-speech)
-    - Daily API key (for video/audio transport)
-    - Mem0 API key (for memory storage and retrieval)
-
-    Environment variables (set in .env or in your terminal using `export`):
-        DAILY_SAMPLE_ROOM_URL=daily_sample_room_url
-        DAILY_API_KEY=daily_api_key
-        OPENAI_API_KEY=openai_api_key
-        ELEVENLABS_API_KEY=elevenlabs_api_key
-        MEM0_API_KEY=mem0_api_key
-
-The bot runs as part of a pipeline that processes audio frames and manages the conversation flow.
-"""
-
-import asyncio
-import os
-import sys
-
-import aiohttp
-from dotenv import load_dotenv
-from loguru import logger
-from runner import configure
-
-from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.pipeline.pipeline import Pipeline
-from pipecat.pipeline.runner import PipelineRunner
-from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
-from pipecat.processors.frameworks.rtvi import RTVIConfig, RTVIObserver, RTVIProcessor
-from pipecat.services.elevenlabs import ElevenLabsTTSService
-from pipecat.services.mem0 import Mem0MemoryService
-from pipecat.services.openai import OpenAILLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
-
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
-
-load_dotenv(override=True)
-
-try:
-    from mem0 import MemoryClient
-except ModuleNotFoundError as e:
-    logger.error(f"Exception: {e}")
-    logger.error(
-        "In order to use Mem0, you need to `pip install mem0ai`. Also, set the environment variable MEM0_API_KEY."
-    )
-    raise Exception(f"Missing module: {e}")
-
-
-async def get_initial_greeting(
-    memory_client: MemoryClient, user_id: str, agent_id: str, run_id: str
-) -> str:
-    """Fetch all memories for the user and create a personalized greeting.
-
-    Returns:
-        A personalized greeting based on user memories
-    """
-    try:
-        # Create filters based on available IDs
-        id_pairs = [("user_id", user_id), ("agent_id", agent_id), ("run_id", run_id)]
-        clauses = [{name: value} for name, value in id_pairs if value is not None]
-        filters = {"AND": clauses} if clauses else {}
-
-        # Get all memories for this user
-        memories = memory_client.get_all(filters=filters, version="v2")
-
-        if not memories or len(memories) == 0:
-            logger.debug(f"!!! No memories found for this user. {memories}")
-            return "Hello! It's nice to meet you. How can I help you today?"
-
-        # Create a personalized greeting based on memories
-        greeting = "Hello! It's great to see you again. "
-
-        # Add some personalization based on memories (limit to 3 memories for brevity)
-        if len(memories) > 0:
-            greeting += "Based on our previous conversations, I remember: "
-            for i, memory in enumerate(memories[:3], 1):
-                memory_content = memory.get("memory", "")
-                # Keep memory references brief
-                if len(memory_content) > 100:
-                    memory_content = memory_content[:97] + "..."
-                greeting += f"{memory_content} "
-
-            greeting += "How can I help you today?"
-
-        logger.debug(f"Created personalized greeting from {len(memories)} memories")
-        return greeting
-
-    except Exception as e:
-        logger.error(f"Error retrieving initial memories from Mem0: {e}")
-        return "Hello! How can I help you today?"
-
-
-async def main():
-    """Main bot execution function.
-
-    Sets up and runs the bot pipeline including:
-    - Daily video transport
-    - Speech-to-text and text-to-speech services
-    - Language model integration
-    - Mem0 memory service
-    - RTVI event handling
-    """
-    # Note: You can pass the user_id as a parameter in API call
-    USER_ID = "pipecat-demo-user"
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
-
-        # Set up Daily transport with video/audio parameters
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Chatbot",
-            DailyParams(
-                audio_out_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-                transcription_enabled=True,
-            ),
-        )
-
-        # Initialize text-to-speech service
-        tts = ElevenLabsTTSService(
-            api_key=os.getenv("ELEVENLABS_API_KEY"),
-            voice_id="pNInz6obpgDQGcFmaJgB",
-        )
-
-        # Initialize Mem0 memory service
-        memory = Mem0MemoryService(
-            api_key=os.getenv("MEM0_API_KEY"),
-            user_id=USER_ID,  # Unique identifier for the user
-            # agent_id="agent1",  # Optional identifier for the agent
-            # run_id="session1", # Optional identifier for the run
-            params=Mem0MemoryService.InputParams(
-                search_limit=10,
-                search_threshold=0.3,
-                api_version="v2",
-                system_prompt="Based on previous conversations, I recall: \n\n",
-                add_as_system_message=True,
-                position=1,
-            ),
-        )
-
-        # Initialize LLM service
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o-mini")
-
-        messages = [
-            {
-                "role": "system",
-                "content": """You are a personal assistant. You can remember things about the person you are talking to.
-                            Some Guidelines:
-                            - Make sure your responses are friendly yet short and concise.
-                            - If the user asks you to remember something, make sure to remember it.
-                            - Greet the user by their name if you know about it.
-                        """,
-            },
-        ]
-
-        # Set up conversation context and management
-        # The context_aggregator will automatically collect conversation context
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
-        rtvi = RTVIProcessor(config=RTVIConfig(config=[]))
-
-        pipeline = Pipeline(
-            [
-                transport.input(),
-                rtvi,
-                context_aggregator.user(),
-                memory,
-                llm,
-                tts,
-                transport.output(),
-                context_aggregator.assistant(),
-            ]
-        )
-
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-            ),
-            observers=[RTVIObserver(rtvi)],
-        )
-
-        @rtvi.event_handler("on_client_ready")
-        async def on_client_ready(rtvi):
-            await rtvi.set_bot_ready()
-
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
-
-            # Get personalized greeting based on user memories. Can pass agent_id and run_id as per requirement of the application to manage short term memory or agent specific memory.
-            greeting = await get_initial_greeting(
-                memory_client=memory.memory_client, user_id=USER_ID, agent_id=None, run_id=None
-            )
-
-            # Add the greeting as an assistant message to start the conversation
-            context.add_message({"role": "assistant", "content": greeting})
-
-            # Queue the context frame to start the conversation
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
-
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            print(f"Participant left: {participant}")
-            await task.cancel()
-
-        runner = PipelineRunner()
-
-        await runner.run(task)
-
-
-if __name__ == "__main__":
-    asyncio.run(main())
--- a/examples/foundational/35-pattern-pair-voice-switching.py
+++ b/examples/foundational/35-pattern-pair-voice-switching.py
@@ -1,230 +0,0 @@
-#
-# Copyright (c) 2024–2025, Daily
-#
-# SPDX-License-Identifier: BSD 2-Clause License
-#
-
-"""Pattern Pair Voice Switching Example with Pipecat.
-
-This example demonstrates how to use the PatternPairAggregator to dynamically switch
-between different voices in a storytelling application. It showcases how pattern matching
-can be used to control TTS behavior in streaming text from an LLM.
-
-The example:
-    1. Sets up a storytelling bot with three distinct voices (narrator, male, female)
-    2. Uses pattern pairs (<voice>name</voice>) to trigger voice switching
-    3. Processes the patterns in real-time as text streams from the LLM
-    4. Removes the pattern tags before sending text to TTS
-
-The PatternPairAggregator:
-    - Buffers text until complete patterns are detected
-    - Identifies content between start/end pattern pairs
-    - Triggers callbacks when patterns are matched
-    - Processes patterns that may span across multiple text chunks
-    - Returns processed text at sentence boundaries
-
-Example usage (run from pipecat root directory):
-    $ pip install "pipecat-ai[daily,openai,cartesia,silero]"
-    $ pip install -r dev-requirements.txt
-    $ python examples/foundational/35-pattern-pair-voice-switching.py
-
-Requirements:
-    - OpenAI API key (for GPT-4o)
-    - Cartesia API key (for text-to-speech)
-    - Daily API key (for video/audio transport)
-
-    Environment variables (.env file):
-        OPENAI_API_KEY=your_openai_key
-        CARTESIA_API_KEY=your_cartesia_key
-        DAILY_API_KEY=your_daily_key
-
-Note:
-    This example shows one application of PatternPairAggregator (voice switching),
-    but the same approach can be used for various pattern-based text processing needs,
-    such as formatting instructions, command recognition, or structured data extraction.
-"""
-
-import asyncio
-import os
-import sys
-
-import aiohttp
-from dotenv import load_dotenv
-from loguru import logger
-from runner import configure
-
-from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.pipeline.pipeline import Pipeline
-from pipecat.pipeline.runner import PipelineRunner
-from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
-from pipecat.services.cartesia import CartesiaTTSService
-from pipecat.services.openai import OpenAILLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.utils.text.pattern_pair_aggregator import PatternMatch, PatternPairAggregator
-
-load_dotenv(override=True)
-
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
-
-# Define voice IDs
-VOICE_IDS = {
-    "narrator": "c45bc5ec-dc68-4feb-8829-6e6b2748095d",  # Narrator voice
-    "female": "71a7ad14-091c-4e8e-a314-022ece01c121",  # Female character voice
-    "male": "7cf0e2b1-8daf-4fe4-89ad-f6039398f359",  # Male character voice
-}
-
-
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
-
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Multi-voice storyteller",
-            DailyParams(
-                audio_out_enabled=True,
-                transcription_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-            ),
-        )
-
-        # Create pattern pair aggregator for voice switching
-        pattern_aggregator = PatternPairAggregator()
-
-        # Add pattern for voice switching
-        pattern_aggregator.add_pattern_pair(
-            pattern_id="voice_tag",
-            start_pattern="<voice>",
-            end_pattern="</voice>",
-            remove_match=True,
-        )
-
-        # Register handler for voice switching
-        def on_voice_tag(match: PatternMatch):
-            voice_name = match.content.strip().lower()
-            if voice_name in VOICE_IDS:
-                voice_id = VOICE_IDS[voice_name]
-                tts.set_voice(voice_id)
-                logger.info(f"Switched to {voice_name} voice")
-            else:
-                logger.warning(f"Unknown voice: {voice_name}")
-
-        pattern_aggregator.on_pattern_match("voice_tag", on_voice_tag)
-
-        # Initialize TTS with narrator voice as default
-        tts = CartesiaTTSService(
-            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id=VOICE_IDS["narrator"],
-            text_aggregator=pattern_aggregator,
-        )
-
-        # Initialize LLM
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
-
-        # System prompt for storytelling with voice switching
-        system_prompt = """You are an engaging storyteller that uses different voices to bring stories to life.
-
-You have three voices to use, but each has a specific purpose:
-
-<voice>narrator</voice>
-This is the default narrator voice. Use this for all narration, descriptions, and non-dialogue text.
-
-<voice>female</voice>
-Use this ONLY for direct speech by female characters (just the quoted text).
-
-<voice>male</voice>
-Use this ONLY for direct speech by male characters (just the quoted text).
-
-IMPORTANT: Switch back to narrator voice immediately after character dialogue.
-
-Here's an EXAMPLE of correct voice usage:
-
-<voice>narrator</voice>
-Sarah spotted her old friend across the café. She couldn't believe her eyes.
-
-<voice>female</voice>
-"Jacob! It's been so long!"
-
-<voice>narrator</voice>
-Sarah exclaimed, jumping up from her seat with a radiant smile.
-
-<voice>male</voice>
-"Sarah, is it really you? I can't believe it!"
-
-<voice>narrator</voice>
-Jacob replied, grinning widely as he walked over to her. The two friends embraced warmly, as if trying to make up for all the years spent apart.
-
-<voice>female</voice>
-"What are you doing in town? Last I heard you were in Seattle."
-
-<voice>narrator</voice>
-She asked, gesturing for him to join her at the table.
-
-FOLLOW THESE RULES:
-1. Always begin with the narrator voice
-2. Only use character voices for the EXACT words they speak (in quotes)
-3. SWITCH BACK to narrator voice for speech tags and all other text
-4. Begin by asking what kind of story the user would like to hear
-5. Create engaging dialogue with distinct characters
-
-Remember: Use narrator voice for EVERYTHING except the actual quoted dialogue."""
-
-        # Set up LLM context
-        messages = [
-            {
-                "role": "system",
-                "content": system_prompt,
-            },
-        ]
-
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
-
-        # Create pipeline
-        pipeline = Pipeline(
-            [
-                transport.input(),
-                context_aggregator.user(),
-                llm,
-                tts,  # TTS with pattern aggregator
-                transport.output(),
-                context_aggregator.assistant(),
-            ]
-        )
-
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-                report_only_initial_ttfb=True,
-            ),
-        )
-
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            logger.info(f"First participant joined: {participant['id']}")
-            await transport.capture_participant_transcription(participant["id"])
-
-            # Start conversation - empty prompt to let LLM follow system instructions
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
-
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            logger.info(f"Participant left: {participant['id']}")
-            await task.cancel()
-
-        logger.info(f"Starting storytelling bot at: {room_url}")
-        logger.info("Join the room to interact with the bot!")
-
-        runner = PipelineRunner()
-        await runner.run(task)
-
-
-if __name__ == "__main__":
-    asyncio.run(main())
--- a/examples/foundational/36-user-email-gathering.py
+++ b/examples/foundational/36-user-email-gathering.py
@@ -1,141 +0,0 @@
-#
-# Copyright (c) 2024–2025, Daily
-#
-# SPDX-License-Identifier: BSD 2-Clause License
-#
-
-import asyncio
-import os
-import sys
-
-import aiohttp
-from dotenv import load_dotenv
-from loguru import logger
-from openai.types.chat import ChatCompletionToolParam
-from runner import configure
-
-from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.pipeline.pipeline import Pipeline
-from pipecat.pipeline.runner import PipelineRunner
-from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.services.cartesia import CartesiaTTSService
-from pipecat.services.openai import OpenAILLMContext, OpenAILLMService
-from pipecat.services.rime import RimeHttpTTSService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
-
-load_dotenv(override=True)
-
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
-
-
-async def store_user_emails(function_name, tool_call_id, args, llm, context, result_callback):
-    print(f"User emails: {args}")
-
-
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
-
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                transcription_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-            ),
-        )
-
-        # Cartesia offers a `<spell></spell>` tags that we can use to ask the user
-        # to confirm the emails.
-        # (see https://docs.cartesia.ai/build-with-sonic/formatting-text-for-sonic/spelling-out-input-text)
-        tts = CartesiaTTSService(
-            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-            aiohttp_session=session,
-        )
-
-        # Rime offers a function `spell()` that we can use to ask the user
-        # to confirm the emails.
-        # (see https://docs.rime.ai/api-reference/spell)
-        # tts = RimeHttpTTSService(
-        #     api_key=os.getenv("RIME_API_KEY", ""),
-        #     voice_id="eva",
-        #     aiohttp_session=session,
-        # )
-
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
-        # You can aslo register a function_name of None to get all functions
-        # sent to the same callback with an additional function_name parameter.
-        llm.register_function("store_user_emails", store_user_emails)
-
-        tools = [
-            ChatCompletionToolParam(
-                type="function",
-                function={
-                    "name": "store_user_emails",
-                    "description": "Store user emails when confirmed",
-                    "parameters": {
-                        "type": "object",
-                        "properties": {
-                            "emails": {
-                                "type": "array",
-                                "description": "The list of user emails",
-                                "items": {"type": "string"},
-                            },
-                        },
-                        "required": ["emails"],
-                    },
-                },
-            )
-        ]
-        messages = [
-            {
-                "role": "system",
-                # Cartesia <spell></spell>
-                "content": "You need to gather a valid email or emails from the user. Your output will be converted to audio so don't include special characters in your answers. If the user provides one or more email addresses confirm them with the user. Enclose all emails with <spell> tags, for example <spell>a@a.com</spell>.",
-                # Rime spell()
-                # "content": "You need to gather a valid email or emails from the user. Your output will be converted to audio so don't include special characters in your answers. If the user provides one or more email addresses confirm them with the user. Enclose all emails with spell(), for example spell(a@a.com).",
-            },
-        ]
-
-        context = OpenAILLMContext(messages, tools)
-        context_aggregator = llm.create_context_aggregator(context)
-
-        pipeline = Pipeline(
-            [
-                transport.input(),
-                context_aggregator.user(),
-                llm,
-                tts,
-                transport.output(),
-                context_aggregator.assistant(),
-            ]
-        )
-
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-                report_only_initial_ttfb=True,
-            ),
-        )
-
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
-            # Kick off the conversation.
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
-
-        runner = PipelineRunner()
-
-        await runner.run(task)
-
-
-if __name__ == "__main__":
-    asyncio.run(main())
--- a/examples/moondream-chatbot/bot.py
+++ b/examples/moondream-chatbot/bot.py
@@ -23,6 +23,7 @@ from pipecat.frames.frames import (
    OutputImageRawFrame,
    SpriteFrame,
    TextFrame,
+    UserImageRawFrame,
    UserImageRequestFrame,
 )
 from pipecat.pipeline.parallel_pipeline import ParallelPipeline
@@ -153,7 +154,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
--- a/examples/news-chatbot/server/news_bot.py
+++ b/examples/news-chatbot/server/news_bot.py
@@ -96,8 +96,8 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-            text_filters=[MarkdownTextFilter()],
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
+            text_filter=MarkdownTextFilter(),
        )

        llm = GoogleLLMService(
--- a/examples/patient-intake/bot.py
+++ b/examples/patient-intake/bot.py
@@ -142,9 +142,7 @@ class IntakeProcessor:
                ]
            )

-    async def list_prescriptions(
-        self, function_name, tool_call_id, args, llm, context, result_callback
-    ):
+    async def start_prescriptions(self, function_name, llm, context):
        print(f"!!! doing start prescriptions")
        # Move on to allergies
        context.set_tools(
@@ -184,12 +182,9 @@ class IntakeProcessor:
        print(f"!!! about to await llm process frame in start prescrpitions")
        await llm.queue_frame(OpenAILLMContextFrame(context), FrameDirection.DOWNSTREAM)
        print(f"!!! past await process frame in start prescriptions")
-        await self.save_data(args, result_callback)

-    async def list_allergies(
-        self, function_name, tool_call_id, args, llm, context, result_callback
-    ):
-        print("!!! doing list allergies")
+    async def start_allergies(self, function_name, llm, context):
+        print("!!! doing start allergies")
        # Move on to conditions
        context.set_tools(
            [
@@ -226,11 +221,8 @@ class IntakeProcessor:
            }
        )
        await llm.queue_frame(OpenAILLMContextFrame(context), FrameDirection.DOWNSTREAM)
-        await self.save_data(args, result_callback)

-    async def list_conditions(
-        self, function_name, tool_call_id, args, llm, context, result_callback
-    ):
+    async def start_conditions(self, function_name, llm, context):
        print("!!! doing start conditions")
        # Move on to visit reasons
        context.set_tools(
@@ -268,11 +260,8 @@ class IntakeProcessor:
            }
        )
        await llm.queue_frame(OpenAILLMContextFrame(context), FrameDirection.DOWNSTREAM)
-        await self.save_data(args, result_callback)

-    async def list_visit_reasons(
-        self, function_name, tool_call_id, args, llm, context, result_callback
-    ):
+    async def start_visit_reasons(self, function_name, llm, context):
        print("!!! doing start visit reasons")
        # move to finish call
        context.set_tools([])
@@ -280,9 +269,8 @@ class IntakeProcessor:
            {"role": "system", "content": "Now, thank the user and end the conversation."}
        )
        await llm.queue_frame(OpenAILLMContextFrame(context), FrameDirection.DOWNSTREAM)
-        await self.save_data(args, result_callback)

-    async def save_data(self, args, result_callback):
+    async def save_data(self, function_name, tool_call_id, args, llm, context, result_callback):
        logger.info(f"!!! Saving data: {args}")
        # Since this is supposed to be "async", returning None from the callback
        # will prevent adding anything to context or re-prompting
@@ -315,7 +303,7 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        )

        # tts = CartesiaTTSService(
@@ -331,10 +319,18 @@ async def main():

        intake = IntakeProcessor(context)
        llm.register_function("verify_birthday", intake.verify_birthday)
-        llm.register_function("list_prescriptions", intake.list_prescriptions)
-        llm.register_function("list_allergies", intake.list_allergies)
-        llm.register_function("list_conditions", intake.list_conditions)
-        llm.register_function("list_visit_reasons", intake.list_visit_reasons)
+        llm.register_function(
+            "list_prescriptions", intake.save_data, start_callback=intake.start_prescriptions
+        )
+        llm.register_function(
+            "list_allergies", intake.save_data, start_callback=intake.start_allergies
+        )
+        llm.register_function(
+            "list_conditions", intake.save_data, start_callback=intake.start_conditions
+        )
+        llm.register_function(
+            "list_visit_reasons", intake.save_data, start_callback=intake.start_visit_reasons
+        )

        fl = FrameLogger("LLM Output")

--- a/examples/telnyx-chatbot/bot.py
+++ b/examples/telnyx-chatbot/bot.py
@@ -54,7 +54,7 @@ async def run_bot(

    tts = CartesiaTTSService(
        api_key=os.getenv("CARTESIA_API_KEY"),
-        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
    )

    messages = [
--- a/examples/telnyx-chatbot/env.example
+++ b/examples/telnyx-chatbot/env.example
@@ -1,3 +1,3 @@
 OPENAI_API_KEY=
 DEEPGRAM_API_KEY=
-CARTESIA_API_KEY=
+ELEVENLABS_API_KEY=
--- a/examples/telnyx-chatbot/requirements.txt
+++ b/examples/telnyx-chatbot/requirements.txt
@@ -1,4 +1,4 @@
-pipecat-ai[openai,silero,deepgram,cartesia]
+pipecat-ai[openai,silero,deepgram,elevenlabs]
 fastapi
 uvicorn
 python-dotenv
--- a/examples/translation-chatbot/bot.py
+++ b/examples/translation-chatbot/bot.py
@@ -144,7 +144,7 @@ async def main():
        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
            voice_id="34dbb662-8e98-413c-a1ef-1a3407675fe7",  # Spanish Narrator Man
-            model="sonic-2",
+            model="sonic-multilingual",
        )

        in_language = "English"
--- a/examples/twilio-chatbot/bot.py
+++ b/examples/twilio-chatbot/bot.py
@@ -74,7 +74,7 @@ async def run_bot(websocket_client: WebSocket, stream_sid: str, testing: bool):

    tts = CartesiaTTSService(
        api_key=os.getenv("CARTESIA_API_KEY"),
-        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
        push_silence_after_stop=testing,
    )

--- a/examples/websocket-server/bot.py
+++ b/examples/websocket-server/bot.py
@@ -97,7 +97,7 @@ async def main():

    tts = CartesiaTTSService(
        api_key=os.getenv("CARTESIA_API_KEY"),
-        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
    )

    messages = [
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -31,7 +31,7 @@ dependencies = [
    "pyloudnorm~=0.1.1",
    "resampy~=0.4.3",
    "soxr~=0.5.0",
-    "openai~=1.67.0"
+    "openai~=1.59.6"
 ]

 [project.urls]
@@ -39,52 +39,48 @@ Source = "https://github.com/pipecat-ai/pipecat"
 Website = "https://pipecat.ai"

 [project.optional-dependencies]
-anthropic = [ "anthropic~=0.49.0" ]
-assemblyai = [ "assemblyai~=0.37.0" ]
-aws = [ "boto3~=1.37.16" ]
+anthropic = [ "anthropic~=0.47.2" ]
+assemblyai = [ "assemblyai~=0.36.0" ]
+aws = [ "boto3~=1.35.99" ]
 azure = [ "azure-cognitiveservices-speech~=1.42.0"]
 canonical = [ "aiofiles~=24.1.0" ]
-cartesia = [ "cartesia~=1.4.0", "websockets~=13.1" ]
-neuphonic = [ "pyneuphonic~=1.5.13", "websockets~=13.1" ]
+cartesia = [ "cartesia~=1.3.1", "websockets~=13.1" ]
 cerebras = []
 deepseek = []
 daily = [ "daily-python~=0.15.0" ]
 deepgram = [ "deepgram-sdk~=3.8.0" ]
 elevenlabs = [ "websockets~=13.1" ]
-fal = [ "fal-client~=0.5.9" ]
+fal = [ "fal-client~=0.5.6" ]
 fish = [ "ormsgpack~=1.7.0", "websockets~=13.1" ]
 gladia = [ "websockets~=13.1" ]
-google = [ "google-cloud-speech~=2.31.1", "google-cloud-texttospeech~=2.25.1", "google-genai~=1.7.0", "google-generativeai~=0.8.4" ]
+google = [ "google-cloud-speech~=2.31.0", "google-cloud-texttospeech~=2.25.0", "google-genai~=1.3.0", "google-generativeai~=0.8.4" ]
 grok = []
 groq = []
 gstreamer = [ "pygobject~=3.50.0" ]
 fireworks = []
 krisp = [ "pipecat-ai-krisp~=0.3.0" ]
 koala = [ "pvkoala~=2.0.3" ]
-langchain = [ "langchain~=0.3.20", "langchain-community~=0.3.20", "langchain-openai~=0.3.9" ]
-livekit = [ "livekit~=0.22.0", "livekit-api~=0.8.2", "tenacity~=9.0.0" ]
+langchain = [ "langchain~=0.3.14", "langchain-community~=0.3.14", "langchain-openai~=0.3.0" ]
+livekit = [ "livekit~=0.19.1", "livekit-api~=0.8.1", "tenacity~=9.0.0" ]
 lmnt = [ "websockets~=13.1" ]
 local = [ "pyaudio~=0.2.14" ]
 moondream = [ "einops~=0.8.0", "timm~=1.0.13", "transformers~=4.48.0" ]
 nim = []
 noisereduce = [ "noisereduce~=3.0.3" ]
 openai = [ "websockets~=13.1" ]
-openpipe = [ "openpipe~=4.48.0" ]
-openrouter = []
+openpipe = [ "openpipe~=4.45.0" ]
 perplexity = []
 playht = [ "pyht~=0.1.12", "websockets~=13.1" ]
 rime = [ "websockets~=13.1" ]
-riva = [ "nvidia-riva-client~=2.19.0" ]
-sentry = [ "sentry-sdk~=2.23.1" ]
+riva = [ "nvidia-riva-client~=2.18.0" ]
+sentry = [ "sentry-sdk~=2.20.0" ]
 silero = [ "onnxruntime~=1.20.1" ]
 simli = [ "simli-ai~=0.1.10"]
 soundfile = [ "soundfile~=0.13.0" ]
-tavus=[]
 together = []
-ultravox = [ "transformers~=4.48.0", "vllm~=0.7.3" ]
 websocket = [ "websockets~=13.1", "fastapi~=0.115.6" ]
 whisper = [ "faster-whisper~=1.1.1" ]
-mem0 = [ "mem0ai~=0.1.76" ]
+openrouter = []

 [tool.setuptools.packages.find]
 # All the following settings are optional:
--- a/src/pipecat/audio/utils.py
+++ b/src/pipecat/audio/utils.py
@@ -18,6 +18,23 @@ def create_default_resampler(**kwargs) -> BaseAudioResampler:
    return SOXRAudioResampler(**kwargs)


+def resample_audio(audio: bytes, original_rate: int, target_rate: int) -> bytes:
+    import warnings
+
+    with warnings.catch_warnings():
+        warnings.simplefilter("always")
+        warnings.warn(
+            "'resample_audio()' is deprecated, use 'create_default_resampler()' instead.",
+            DeprecationWarning,
+        )
+
+    if original_rate == target_rate:
+        return audio
+    audio_data = np.frombuffer(audio, dtype=np.int16)
+    resampled_audio = soxr.resample(audio_data, original_rate, target_rate)
+    return resampled_audio.astype(np.int16).tobytes()
+
+
 def mix_audio(audio1: bytes, audio2: bytes) -> bytes:
    data1 = np.frombuffer(audio1, dtype=np.int16)
    data2 = np.frombuffer(audio2, dtype=np.int16)
--- a/src/pipecat/frames/frames.py
+++ b/src/pipecat/frames/frames.py
@@ -634,15 +634,6 @@ class FunctionCallInProgressFrame(SystemFrame):
    function_name: str
    tool_call_id: str
    arguments: str
-    cancel_on_interruption: bool
-
-
-@dataclass
-class FunctionCallCancelFrame(SystemFrame):
-    """A frame to signal a function call has been cancelled."""
-
-    function_name: str
-    tool_call_id: str


@dataclass
@@ -662,19 +653,13 @@ class TransportMessageUrgentFrame(SystemFrame):

@dataclass
 class UserImageRequestFrame(SystemFrame):
-    """A frame to request an image from the given user. The frame might be
-    generated by a function call in which case the corresponding fields will be
-    properly set.
-
-    """
+    """A frame user to request an image from the given user."""

    user_id: str
    context: Optional[Any] = None
-    function_name: Optional[str] = None
-    tool_call_id: Optional[str] = None

    def __str__(self):
-        return f"{self.name}(user: {self.user_id}, function: {self.function_name}, request: {self.tool_call_id})"
+        return f"{self.name}, user: {self.user_id}"


@dataclass
@@ -704,11 +689,10 @@ class UserImageRawFrame(InputImageRawFrame):
    """An image associated to a user."""

    user_id: str
-    request: Optional[UserImageRequestFrame] = None

    def __str__(self):
        pts = format_pts(self.pts)
-        return f"{self.name}(pts: {pts}, user: {self.user_id}, size: {self.size}, format: {self.format}, request: {self.request})"
+        return f"{self.name}(pts: {pts}, user: {self.user_id}, size: {self.size}, format: {self.format})"


@dataclass
--- a/src/pipecat/pipeline/runner.py
+++ b/src/pipecat/pipeline/runner.py
@@ -40,18 +40,12 @@ class PipelineRunner(BaseObject):
        task.set_event_loop(self._loop)
        await task.run()
        del self._tasks[task.name]
-
-        # Cleanup base object.
-        await self.cleanup()
-
        # If we are cancelling through a signal, make sure we wait for it so
        # everything gets cleaned up nicely.
        if self._sig_task:
            await self._sig_task
-
        if self._force_gc:
            self._gc_collect()
-
        logger.debug(f"Runner {self} finished running {task}")

    async def stop_when_done(self):
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Mark Backman	10e31958fd	Add flush_audio() to LMNTTTSService	2025-03-07 15:42:31 -05:00
Mark Backman	373ffc48b6	Add placeholders for Gladia's set_model and set_language methods	2025-03-07 15:38:23 -05:00
Mark Backman	5ae6229c03	Add flush_audio() to PlayHTTTSService	2025-03-07 15:26:47 -05:00
Mark Backman	615cbe966a	Add set_model to AssemblySTTService	2025-03-07 15:18:10 -05:00
Mark Backman	3caccab608	Azure STT and TTS: Satisfy requirements for set_model, set_language, flush_audio	2025-03-07 15:07:50 -05:00
Mark Backman	78d3c77369	Added a flush_audio method to FishTTSService	2025-03-07 14:28:19 -05:00
Mark Backman	44b3e6cefa	Fix: GoogleSTTService's set_languages method should be set_language to satisfy base class requirement	2025-03-07 14:28:19 -05:00
Mark Backman	20ea073398	Move flush_audio to WebsocketTTSService base class	2025-03-07 14:28:19 -05:00