Commit Graph

6348 Commits

Author SHA1 Message Date
Filipi Fuchter
600cd18cb7 Ensure to push LLMFullResponseEndFrame if the sentence is empty. 2025-11-18 19:50:14 -03:00
kompfner
a60618b0ca Merge pull request #3080 from pipecat-ai/pk/assistant-aggregator-handles-mixed-includes-inter-frame-spaces-text
`LLMAssistantAggregator` now properly aggregates text that might be a…
2025-11-18 15:24:27 -05:00
Paul Kompfner
3d21faaac2 LLMAssistantAggregator now properly aggregates text that might be a mix of includes_inter_frame_spaces=True and includes_inter_frame_spaces=False frames 2025-11-18 15:12:25 -05:00
Mark Backman
d1eb837890 Merge pull request #3081 from pipecat-ai/mb/fix-30-tts-text-frame-log
Fix foundational 30 example to output TTSTextFrames synced to audio
2025-11-18 14:10:56 -05:00
Mark Backman
153201542b Fix foundational 30 example to output TTSTextFrames synced to audio 2025-11-18 13:29:06 -05:00
Filipi da Silva Fuchter
9137e50043 Merge pull request #3053 from pipecat-ai/filipi/function_calls
Ensure that the function call results respect the previous LLM context.
2025-11-18 14:59:01 -03:00
Aleix Conchillo Flaqué
c1573c1f76 Merge pull request #3078 from pipecat-ai/aleix/llm-context-create-image-audio-async
LLMContext: create_image_message/create_audio_message are now async
2025-11-18 09:06:51 -08:00
Aleix Conchillo Flaqué
9f45ad4d2e LLMContext: create_image_message/create_audio_message are now async 2025-11-18 09:04:40 -08:00
Filipi Fuchter
fccc91e923 Searching in both _function_calls_context_messages and context messages when updating the result. 2025-11-18 11:50:28 -03:00
Filipi Fuchter
a510b276e6 Ensure that the function call results respect the previous LLM context. 2025-11-18 11:37:57 -03:00
Mark Backman
6481094638 Merge pull request #3058 from pipecat-ai/mb/add-camera-screen-support-smallwebrtc
Add camera and screen capture support to dev runner for SmallWebRTC
2025-11-18 09:22:36 -05:00
Mark Backman
3132e12265 Add camera and screen capture support to dev runner for SmallWebRTC 2025-11-18 09:19:13 -05:00
Aleix Conchillo Flaqué
12af3f79d0 Merge pull request #3060 from pipecat-ai/aleix/consumer-queue-frames
ConsumerProcessor: queue frames internally instead of pushing them
2025-11-18 00:54:18 -08:00
Aleix Conchillo Flaqué
4835617b16 ConsumerProcessor: queue frames internally instead of pushing them 2025-11-17 23:52:09 -08:00
Aleix Conchillo Flaqué
9283108240 Merge pull request #3073 from pipecat-ai/aleix/base-text-filter-only-filter
BaseTextFilter: only require subclasses to implement filter()
2025-11-17 23:29:26 -08:00
kompfner
515eaeeb1a Merge pull request #3074 from pipecat-ai/pk/tweak-moondream-example
Update Moondream example so that Moondream service output makes it in…
2025-11-17 16:52:18 -05:00
Paul Kompfner
5095fc6a64 Update Moondream example so that Moondream service output makes it into the context, even if the TTS service is disabled 2025-11-17 15:16:19 -05:00
Aleix Conchillo Flaqué
7eedb33d50 BaseTextFilter: only require subclasses to implement filter() 2025-11-17 11:23:47 -08:00
Filipi da Silva Fuchter
47f78df497 Merge pull request #3071 from pipecat-ai/filipi/small_webrtc_custom_data
Passing the custom request_data to the SmallWebRTCRunnerArguments body.
2025-11-17 15:50:11 -03:00
Filipi Fuchter
74154b26a2 Mentioning the SmallWebRTCTransport fix in the readme. 2025-11-17 15:39:07 -03:00
Filipi Fuchter
0c3c26b7b8 Passing the custom request_data to the SmallWebRTCRunnerArguments body. 2025-11-17 15:20:09 -03:00
kompfner
64417ef4ff Merge pull request #3061 from pipecat-ai/pk/greatly-simplify-inter-frame-spaces-logic
D'oh! My TTS "inter-frame-spaces" logic was *way* overcomplicated (an…
2025-11-17 10:47:56 -05:00
Paul Kompfner
f3b254e335 D'oh! My TTS "inter-frame-spaces" logic was *way* overcomplicated (and fundamentally mistaken, though it happened to work)
Now:
- For TTS word-by-word output and `TTSSpeakFrames`: `TTSTextFrame`s' have `includes_inter_frame_spaces=False`.
- For all other TTS output: `TTSTextFrame` pass through the received text frames' `includes_inter_frame_spaces` value. So far, this value has always been `True`: LLMs send text chunks already containing all necessary spaces.
- `LLMTextFrame`s set `includes_inter_frame_spaces=False` at init time, per the aforementioned assumption.
2025-11-17 10:14:28 -05:00
Filipi da Silva Fuchter
f27119a712 Merge pull request #3069 from pipecat-ai/filipi/fix_riva
Fixing RivaTTSService error handler.
2025-11-17 11:48:15 -03:00
Filipi da Silva Fuchter
a5145be16e Merge pull request #3038 from pipecat-ai/filipi/flux_improvements
Deepgram Flux improvements
2025-11-17 09:57:43 -03:00
Filipi Fuchter
b104a59b10 Mentioning the Deepgram Flux improvements in the changelog. 2025-11-17 09:54:39 -03:00
Filipi Fuchter
04dbbabc03 Introduced a minimum confidence parameter in DeepgramFluxSTTService to avoid generating transcriptions below a defined threshold. 2025-11-17 09:54:30 -03:00
Filipi Fuchter
19cc0177b8 Refactored DeepgramFluxSTTService to automatically reconnect if sending a message fails. 2025-11-17 09:54:20 -03:00
Filipi Fuchter
77cd106795 Extracted the logic for retrying connections, and create a new send_with_retry method inside WebSocketService. 2025-11-17 09:54:08 -03:00
Filipi Fuchter
9bf88bbf14 Fixing RivaTTSService error handler. 2025-11-17 07:43:30 -03:00
Mark Backman
35ff44b799 Merge pull request #3059 from pipecat-ai/mb/remove-llm-tracing-fallback 2025-11-14 14:07:40 -05:00
Angad Singh
d1116d149e feat: Add ErrorFrame emission to TTS/STT services for pipeline error detection (#2881)
* feat: Add ErrorFrame emission to TTS/STT services for pipeline error detection

- Add ErrorFrame emission to all major TTS/STT services during initialization and runtime failures
- Services updated: Cartesia, ElevenLabs, Deepgram, AssemblyAI, Rime, Azure
- ErrorFrame objects emitted with fatal=False for graceful degradation
- Enables on_pipeline_error event handler to detect service failures programmatically
- Add comprehensive pytest test suite to verify ErrorFrame emission
- Fixes issue where services failed gracefully but didn't emit ErrorFrame objects

This allows developers to implement real-time error monitoring and alerting
using the on_pipeline_error event handler introduced in v0.0.90.

* Update STT and TTS services to use consistent error handling pattern

- Improves error handling consistency across all services

* Add changelog entry for STT/TTS error handling improvements

* Linting issues Resolved

* Azure STT ErrorFrames added with consistent patterns

* Cartesia STT and Deepgram STT; additional fixes made

* Removed Fatal Flags across services, removed duplication

* Moving the changelog entry to the correct place.

* Refactoring some classes to use yield instead of push_error directly.

* Fixing ruff format.

---------

Co-authored-by: Filipi Fuchter <filipi87@gmail.com>
2025-11-14 15:03:05 -03:00
Mark Backman
d01876ee60 Remove fallbacks in traced_llm 2025-11-14 12:13:49 -05:00
Mark Backman
74a0e8c88d Merge pull request #3050 from ai-coustics/aic-vad-analyzer
feat(ai-coustics): add ai-coustics integrated VAD
2025-11-14 08:11:15 -05:00
Corvin Jaedicke
fbbad27d37 add changelog info 2025-11-14 13:30:06 +01:00
kompfner
e83ac82bf3 Merge pull request #3042 from pipecat-ai/pk/follow-up-inter-frame-spaces
Follow-up to #3041
2025-11-13 11:03:06 -05:00
Mark Backman
d78d38ce44 Merge pull request #3039 from pipecat-ai/mb/update-google-gemini-tts
Update GeminiTTSService for streaming, other Google TTS improvements
2025-11-13 10:33:46 -05:00
Mark Backman
edbf96b3c5 Update GeminiTTSService for streaming, other Google TTS improvements 2025-11-13 10:22:34 -05:00
Paul Kompfner
8851d18f92 Tweak the LLM prompt again to try to fix the issue of LLMs sometimes omitting punctuation in their output. 2025-11-13 10:02:33 -05:00
Mark Backman
d823a3edec Merge pull request #3040 from pipecat-ai/mb/11labs-realtime-stt
Add ElevenLabsRealtimeSTTService
2025-11-13 09:53:34 -05:00
Mark Backman
0e37658f8d Add ElevenLabsRealtimeSTTService 2025-11-13 09:49:05 -05:00
Corvin Jaedicke
2fab3e2286 fix formatting 2025-11-13 14:39:26 +01:00
Corvin Jaedicke
a7b2052b38 add ai-coustics VAD 2025-11-13 14:20:35 +01:00
Mark Backman
6d0e99c3b8 Merge pull request #3044 from rimelabs/rime-hin-lanaguge-support
Add support for Hindi language in RIme TTS service
2025-11-12 21:13:01 -05:00
gokuljs
fe25465987 changelog update 2025-11-13 07:16:36 +05:30
gokuljs
498e9ca4f6 Add support for Hindi language in RIme TTS service 2025-11-13 04:33:22 +05:30
Paul Kompfner
1802f949ef Fix an issue with some examples where punctuation was missing from the LLM output, by tweaking the LLM prompt. 2025-11-12 17:12:03 -05:00
Paul Kompfner
1ad6405ebb Override includes_inter_frame_spaces in:
- `GoogleHttpTTSService`
- `OpenAITTSService`

The reason I skipped this work in an earlier PR was because these services seemed to be emitting long, punctuation-free text frames. It turns out that the issue was with the LLM prompt, though, resulting in the LLM nondeterministically excluding all punctuation. An upcoming commit will address that prompt issue.
2025-11-12 17:07:43 -05:00
kompfner
4c25555396 Merge pull request #3041 from pipecat-ai/pk/apply-includes-inter-frame-spaces-wherever-necessary
Apply `includes_inter_frame_spaces = True` in all LLM and TTS service…
2025-11-12 16:49:14 -05:00
Paul Kompfner
5222ff99de Apply includes_inter_frame_spaces = True in all LLM and TTS services that need it.
Note that for `LLMTextFrame`s, the right behavior is pretty much always `includes_inter_frame_spaces = True`. I decided *not* to go ahead and make that the default for `LLMTextFrame`s, though, simply to not introduce a subtle behavior change for creative/unexpected use-cases that were relying on text in hand-crafted `LLMTextFrame`s being handled a certain way. Ditto for `TTSTextFrame`s.

Also, fix an issue in `NeuphonicTTSService` where it wasn't pushing `TTSTextFrame`s.

Also, fix the broken `SarvamHttpTTSService` example.

Also, add a couple of missing examples.
2025-11-12 15:10:11 -05:00