Adds an field to LLMContextSummarizationConfig that allows
routing summarization to a separate LLM service (e.g., Gemini Flash)
instead of the pipeline's primary model. This avoids paying for
expensive inference when compressing context in long-running sessions.
Allows applications to customize how the summary is wrapped when
injected into context (e.g., XML tags, custom delimiters) so system
prompts can distinguish summaries from live conversation.
Add deprecation warnings to start_processing_metrics() and
stop_processing_metrics() on FrameProcessorMetrics and FrameProcessor.
Mark ProcessingMetricsData as deprecated in docstring. All existing
behavior is preserved — the warnings inform users that these will be
removed in a future version.
- Fix speaker diarization: Add field alias for speaker_label → speaker
mapping in TurnMessage model
- Add warning for non-optimal min_end_of_turn_silence_when_confident
values (recommends 100ms for best latency)
- Improve max_turn_silence override warning message clarity
- Update custom prompt warning (remove 88% accuracy claim)
- Add comprehensive logging for debugging:
- Log final connection params after modifications
- Log WebSocket URL and parsed parameters
- Log speaker field in transcripts
- Log text sent to LLM with speaker formatting
- Support dynamic configuration updates via STTUpdateSettingsFrame:
- keyterms_prompt (when AssemblyAI API supports it)
- prompt
- max_turn_silence
- min_end_of_turn_silence_when_confident
- Add InterruptionFrame handling with stop_all_metrics()
- Add processing metrics (start/stop) at response boundaries
- Fix agent transcript handling for voice and text modalities:
- Voice mode: push LLMTextFrame (append_to_context=False) and
TTSTextFrame for deltas, skip duplicated final text
- Text mode: push LLMTextFrame with proper response lifecycle,
no TTSTextFrame (downstream TTS handles audio)
- Add output_medium parameter to AgentInputParams and OneShotInputParams
- Improve TTFB measurement using VAD speech end time
- Update example with user turn strategies and transcript events
- Add text-only output example (50a-ultravox-realtime-text.py)
Move the sentence vs token aggregation concern into text aggregators
so all text flows through them regardless of mode. This enables
pattern detection and tag handling to work in TOKEN mode.
- Add TextAggregationMode enum (SENTENCE, TOKEN) as the user-facing
TTS setting, separate from the internal AggregationType
- Add TOKEN mode support to Simple, SkipTags, and PatternPair aggregators
- Add text_aggregation_mode parameter to TTSService and all TTS subclasses
- Deprecate aggregate_sentences in favor of text_aggregation_mode
- Merge TTSService._process_text_frame() into a single codepath
Add TextAggregationMetricsData measuring the time from the first LLM
token to the first complete sentence, representing the latency cost of
sentence aggregation in the TTS pipeline.
- Wire up passing speed setting to Groq, even though only a value of 1.0 is supported today
- Update the 55y example to switch voices instead of changing speed
- Add a 55zn example to exercise runtime updates of Groq STT
The only (rare) exception—where a service directly still needs to directly call `self._sync_model_name_to_metrics()`—is when the model name need to be "pulled" from another field (or nested field) in settings up to settings.model on a settings update. This only occurs in Deepgram services, where we use the voice as the model name.
This change has the side-effect of bringing model name to metrics for a number of services that were accidentally omitting it before.
This was added in 31daa889e8, but only
to `RimeTTSService`, not to `RimeNonJsonTTSService. Bringing these
to parity means that users switching between the two, with the same
inputs, have more consistent vocalization behaviors.
Introduce a generic TurnMetricsData class for turn detection metrics,
replacing the service-specific SmartTurnMetricsData (now deprecated).
Add end-to-end processing time measurement to KrispVivaTurn, tracking
the interval from VAD speech-to-silence transition to model threshold
crossing. Consume metrics in the strategy _handle_input_audio path
so they are pushed immediately when fresh.
The Krisp VIVA SDK v1.8.0 requires a license key in globalInit(). Add
api_key parameter to KrispVivaSDKManager, KrispVivaTurn, and
KrispVivaFilter with fallback to KRISP_API_KEY env var. Maintain
backwards compatibility with older SDK versions by catching TypeError
and falling back to the old 3-arg signature.
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
These frames were falling through to the else branch and being pushed
downstream, unlike TranscriptionFrame which is explicitly consumed.
This aligns with how the assistant aggregator already filters them.
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.
