- 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.
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.
- Move `CommitStrategy` up in the file so it could be used by `ElevenLabsRealtimeSTTSettings`
- Fix a bug where `run_tts` would erroneously try to reconnect if a reconnection was already in flight (like a reconnection triggered by `_update_settings`)
HumeTTSService now stores its params (description, speed, trailing_silence) in a proper `HumeTTSSettings` dataclass instead of a separate `_params` Pydantic model, making it work with `TTSUpdateSettingsFrame(update=...)`. The old `update_setting(key, value)` method is kept but deprecated.
Also removes the unused no-op `TTSService.update_setting` base method, which was never called by the `TTSUpdateSettingsFrame` pipeline.
The dataclass-based API (`*UpdateSettingsFrame(update=*Settings(...))`) is the preferred path since 0.0.103. The dict path still works but now emits a `DeprecationWarning`.
Change `TTSSettings.language` and `STTSettings.language` from `Any` to `Language | str | _NotGiven`. Add `language_to_service_language` base method and centralized `isinstance`-guarded conversion in `STTService._update_settings` (mirroring TTS). Update the TTS guard from `is not None` to `isinstance(…, Language)` so raw strings pass through unchanged.
Remove now-redundant per-service language conversion from `_update_settings` overrides (ElevenLabs, Azure, Fal, Whisper). Add `language_to_service_language` to Azure STT so the centralized conversion picks it up. Fix AWS and NVIDIA STT `__init__` to convert language at construction time, then simplify their runtime accessors to read `_settings.language` directly.
Note that for services that previously handled applying updates (through methods like `set_model` and `set_language`), we're keeping the update-applying logic (some or most of which is already well-tested) and expanding it to cover all relevant settings fields. Services under this bucket are:
- Deepgram STT
- Deepgram Sagemaker STT
- Elevenlabs STT
- Google STT
- Gradium STT
- OpenAI STT
- Speechmatics STT
Now that all services use typed `ServiceSettings` objects, this removes the interim scaffolding that supported both dict-based and typed settings paths in parallel. Specifically: removes old dict-based `_update_settings(settings: Mapping)` methods from base classes, removes `isinstance(self._settings, ServiceSettings)` guards, simplifies `process_frame` branching, and renames `_update_settings_from_typed` to `_update_settings` across all ~30 service implementations. Also renames the no-arg `_update_settings()` helper on realtime services to `_send_session_update()` to avoid collision, adds `from_mapping` overrides on `GoogleLLMSettings` and `AnthropicLLMSettings` for ThinkingConfig dict-to-object conversion, and replaces a broken no-arg `_update_settings()` call in Gemini Live with a TODO.
- NvidiaSTTService.set_model: convert to proper DeprecationWarning (model can't change at runtime for Riva streaming STT)
- NvidiaTTSService.set_model: same treatment for Riva TTS
- NvidiaSegmentedSTTService.set_model: remove — base class now routes through _update_settings_from_typed which re-creates the recognition config
- GeminiTTSService.set_voice: remove — move AVAILABLE_VOICES validation into _update_settings_from_typed so it fires on both legacy and new paths
Standardize all STT, TTS, and LLM service classes to declare `_settings` with the narrowed Settings type as a class-level annotation. This gives editors and type checkers the specific type when hovering or autocompleting on `self._settings` in each service and its subclasses. Inline `self._settings: Type = ...` assignments are replaced with plain `self._settings = ...`.
`filter_incomplete_user_turns` and `user_turn_completion_config` were only handled in the legacy dict-based `_update_settings` code path. This adds them to `LLMSettings` and introduces `LLMService._update_settings_from_typed` so the typed path handles them too.
Does not (yet) touch `InputParams`, to avoid scope creep and touching something currently part of the public API. But there is a lot of overlap between `*Settings` object fields and `InputParams` fields.
Other than discoverability/typing, these are some other improvements brought by this refactor:
- There is now a single code path (see `_update_settings_from_typed`) where services can respond to settings changes (by, say, reconnecting if needed), improving maintainability and guaranteeing one and only one reconnection no matter which settings changed
- `set_language`/`set_model`/`set_voice`—which we're assuming are usable as public methods, though *not* recommended over `*UpdateSettingsFrame`—all use the same code path as settings updates. They're also now all consistent in that, if a service needs to respond to a change (by, say, reconnecting if needed), any of these methods will kick off that process. Note that this is technically a behavior change.
- Several services now properly react to changed settings by reconnecting:
- `AWSTranscribeSTTService`
- `AzureSTTService`
- `SonioxSTTService`
- `GladiaSTTService`
- `SpeechmaticsSTTService`
- `AssemblyAISTTService`
- `CartesiaSTTService`
- `FishAudioTTSService` (would previously only reconnect when `model` changed)
- `GoogleSTTService`
- `SpeechmaticsSTTService` (which previously only handled *some* settings updates through a nonstandard public `update_params` method)
- `GradiumSTTService`
- `NvidiaSegmentedSTTService` (which previously only handled changes to language)
- Bookkeeping across various services has been reduced, mostly by deduping ivars; the `self._settings` ivar is treated as the source of truth
NOTE: I pretty much guarantee that there are services missed in this PR in terms of bringing to consistency with how updates are handled (like whether changes in certain fields trigger reconnects when they need to). We can squash remaining inconsistencies as we stumble onto them, service by service. The goal here is to get things *mostly* in order, and establish the infrastructure and patterns we'll need going forward.
OpenAI's AsyncStream uses close() while async generators (e.g. from
OpenPipe) use aclose(). Replace direct async-with on the stream with a
helper that handles both protocols.
Adds opt-in keepalive_timeout and keepalive_interval params to
WebsocketSTTService. When enabled, a background task sends silent audio
(or a service-specific protocol message) when the connection has been
idle, preventing server-side timeout disconnects.
Subclasses override _send_keepalive(silence) to wrap the silence in
their wire format. The default sends raw PCM bytes.
Enables keepalive for ElevenLabs (10s), Gladia (20s), and Soniox (1s),
replacing their per-service custom keepalive tasks.
