Audio filters like RNNoise, KrispViva, and AIC return empty bytes while
buffering audio to accumulate their required frame size. These empty
frames were flowing downstream, causing misleading "Empty audio frame
received for STT service" warnings.
Skip the frame in BaseInputTransport when audio is empty, preventing
unnecessary processing in VAD and downstream processors.
Fixes#3517
PR #3776 replaced manual timestamp tracking with stop_ttfb_metrics() in
the timeout handler, but without an end_time it uses time.time() at
timeout expiry—producing TTFB = timeout + stop_secs (~2.2s) instead of
the actual transcript latency.
Restore _last_transcript_time tracking so the timeout handler measures
to when the transcript arrived, and skip reporting if none arrived.
Before this change, settings updates were often not applied. For example, a `TTSUpdateSettingsFrame` queued while the bot was speaking would only have an effect at the end of the bot's reply, and any interruption before the end of the reply would "cancel" the update.
This makes each service-specific field individually visible to the delta/update mechanism (`apply_update`, `given_fields`) and removes the need for complex sync logic between `input_params` and top-level fields like `model`.
- Soniox: replace `input_params: SonioxInputParams` with 8 individual fields, simplify `_update_settings` by removing model sync logic, remove unused `is_given` import
- Gladia: replace `input_params: GladiaInputParams` with 11 individual fields, resolve deprecated `language` → `language_config` at init time rather than at `_prepare_settings` time
- Storage mode: for use in `self._settings`. All fields should be specified, i.e. should not be `NOT_GIVEN`.
- Delta mode: for use in `*UpdateSettingsFrame`.
In service of this, this commit:
- Adds a runtime check that all fields are specified in storage mode
- Updates all services to specify all fields in stored settings
- Updates all services to no longer check for `is_given` in stored settings (not necessary anymore)
- Updates relevant docstrings
- Renames `update` to `delta` in `*UpdateSettingsFrame`
- Updates community integrations guide
Move start_processing_metrics from run_stt (called per audio chunk,
producing noisy 0ms logs) to _receive_messages when the first final
token arrives for a new utterance. The existing stop_processing_metrics
in send_endpoint_transcript completes the pair, giving a meaningful
measurement of time from first recognition to finalized transcript.
Commit 859cd7c9 refactored STT TTFB measurement to use the base class
start_ttfb_metrics/stop_ttfb_metrics, which are gated behind
can_generate_metrics(). Soniox and AWS Transcribe never overrode this
method (default returns False), so TTFB was silently never reported.
Use wildcard `*UpdateSettingsFrame` to cover all frame types. Clarify that NOT_GIVEN only appears in update deltas, not in the service's current settings state.
Update docstrings for ServiceSettings, LLMSettings, TTSSettings, and STTSettings to make clear these capture only the subset of service configuration that can be changed while the pipeline is running via UpdateSettingsFrame, not all constructor parameters.
Replace self-referential `pipecat-ai[local-smart-turn-v3]` extra in core
dependencies with the actual packages (`transformers`, `onnxruntime`).
Self-referential extras are not supported by Poetry and cause dependency
resolution failures. Since these are required by the default turn stop
strategy (LocalSmartTurnAnalyzerV3), they belong in core dependencies.
- Remove `local-smart-turn-v3` optional extra from pyproject.toml
- Remove try/except ModuleNotFoundError guard (now always installed)
- Remove `--extra local-smart-turn-v3` from CI workflows
When the InterruptionFrame does not complete within the timeout the
caller was stuck in an infinite loop logging warnings. Now the event
is set after the first timeout so the processor can continue.
Also adds a keyword timeout parameter so callers can customize the
wait duration.
- indicate clearly that it's not meant for public use
- make it clear the `self._settings` is the single source of truth for model information
- set the stage for an upcoming change where `AIService` subclasses won't have to ever worry about explicitly calling an `AIService` method to sync model name to metrics
Across all services, switch from accessing `self._model_name` or `self.model_name` in favor of `self._settings.model`.
Adds a TTS service that connects to Deepgram models deployed on AWS
SageMaker endpoints via HTTP/2 bidirectional streaming. Supports the
Deepgram TTS protocol (Speak, Flush, Clear, Close) over the BiDi
client, with interruption handling and per-turn TTFB metrics.
Updates the example and env.example with separate STT/TTS endpoint names.
- AWSNovaSonicLLMService: new `AWSNovaSonicLLMSettings` with `voice_id` and `endpointing_sensitivity`; remove `self._params` entirely, storing audio I/O config as plain instance variables
- NeuphonicHttpTTSService: reuse `NeuphonicTTSSettings`; use inherited `language` field instead of bespoke `lang_code`
- NvidiaTTSService: new `NvidiaTTSSettings` with `quality`
- PiperTTSService / PiperHttpTTSService: new `PiperTTSSettings` / `PiperHttpTTSSettings` (no extra fields)
- SpeechmaticsTTSService: new `SpeechmaticsTTSSettings` with `max_retries`
Also remove redundant `lang_code` from `NeuphonicTTSSettings` (both WS and HTTP services now use the inherited `TTSSettings.language` field, with automatic enum conversion via the base class).
HTTP services (Neuphonic HTTP, Piper HTTP, Speechmatics) don't override `_update_settings` since the base class applies changes to `self._settings` and subsequent requests read from it automatically.
Also:
- remove unnecessary pass-through `_update_settings` implementation in `FalSTTService`
- warn that `AsyncAITTSService` doesn't currently support runtime settings updates
- update how `GradiumTTSService._update_settings` checks for voice changes
- remove a couple of unnecessary args (because they specified defaults) in other examples
ThinkingConfig was defined as an inner class on the service but referenced in the Settings dataclass declared before the service class, causing a crash at import time. Move ThinkingConfig to a standalone class defined before Settings, and keep a class attribute alias for backward compatibility.
