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.
Eliminate custom _emit_stt_ttfb_metric and manual timestamp tracking in
STTService by reusing FrameProcessor's start_ttfb_metrics/stop_ttfb_metrics
with new start_time/end_time parameters. This keeps the chronological
start→stop ordering and removes _speech_end_time and _last_transcription_time
state from STTService.
Remove the deprecation warning and __post_init__ override. Also fix the
default value for remote_participants to use field(default_factory=dict)
instead of None.
Add write_transport_frame() hook to BaseOutputTransport so subclasses
can handle custom frame types that flow through the audio queue. Add
DailySIPTransferFrame and DailySIPReferFrame as DataFrame subclasses
that queue with audio, ensuring SIP operations execute only after the
bot finishes its current utterance. Override write_transport_frame in
DailyOutputTransport to dispatch these frames to the existing
sip_call_transfer() and sip_refer() client methods.
Also switch DailyOutputTransport.send_message error handling from
logger.error to push_error for consistency.
Every `*Settings` dataclass field whose default is `NOT_GIVEN` now carries `_NotGiven` in its type union so the type system accurately reflects the three-state semantics (real value, `None` where applicable, or not-yet-specified). Fields previously typed as bare `Any`, `str`, `float`, `bool`, `list`, `dict`, or `Optional[X]` are now narrowed to the specific type from the corresponding `InputParams` Pydantic model.
RTVIObserver previously filtered out all upstream frames to avoid
duplicate messages from broadcasted frames. This caused upstream-only
frames to be silently ignored. Instead, add a `broadcasted` field to
the Frame base class that is set by broadcast_frame() and
broadcast_frame_instance(), and only skip upstream copies of
broadcasted frames.
The CI was failing because the runner's package index was stale,
causing a 404 when fetching libasound2-dev (a dependency of
portaudio19-dev). Running apt-get update first refreshes the index.
