MultiSpeakerAdapter is an adapter that allows to detect and suppress background speakers. It needs STT with diarization capability and works f

Initialize SLNG STT. Args: api_key: SLNG API key for authentication. model: SLNG model identifier (for examp

Create a new instance of Deepgram STT. Args: model: The Deepgram model to use for speech recognition. Defaults to "nova-3".

Create a new instance of Deepgram STT. Args: model: The Deepgram model to use for speech recognition. Defaults to "flux-general-e

Create a new instance of Camb.ai TTS. ``api_key`` must be set to your Camb.ai API key, either using the argument or by setti

Baseten Speech-to-Text provider. Connects to a Baseten Whisper Streaming WebSocket model for real-time transcription. Works with bot

Initialize a RealtimeModel for Phonic's Realtime API. Args: api_key: Phonic API key. If not provided, reads from PHONIC_

Create a new instance of AWS Bedrock LLM. ``api_key`` and ``api_secret`` must be set to your AWS Access key id and secret access ke

Create a new instance of AWS Polly TTS. ``api_key`` and ``api_secret`` must be set to your AWS Access key id and secret access key,

Instantiate a new RealtimeModel. Args: model (REALTIME_MODELS | str): Bedrock model ID for realtime inference. Defaults to "amazo

Initialize the PersonaPlex RealtimeModel. Args: base_url: WebSocket URL of the PersonaPlex server (e.g. "ws://loc

Create a new instance of the xAI TTS. See [xAI TTS Documentation Link] for more documentation on all of these options. Args

Create a new instance of Smallest AI Pulse STT. Args: model: STT model to use. Currently only "pulse" is available. l

Initialize the Hume AI TTS client. Options will be used for all future synthesis (until updated with update_options). Args:

Create a new instance of ElevenLabs STT. Args: api_key (NotGivenOr[str]): ElevenLabs API key. Can be set via argument or

Create a new instance of Cerebras LLM. ``api_key`` must be set to your Cerebras API key, either using the argument or by setting

Configuration options for the SimpliSmart STT (Speech-to-Text) engine. Note: Streaming transcription is not publicly ava

Initialize SimpliSmart TTS. SimpliSmart hosts multiple TTS models. The model name determines which endpoint and payload format to use

Create a new instance of LMNT TTS. See: https://docs.lmnt.com/api-reference/speech/synthesize-speech-bytes Args:

Initialize instance of Soniox Speech-to-Text API service. Args: api_key: Soniox API key, if not provided, will look for SONIOX_AP

Initialize instance of Soniox Text-to-Speech API service. Args: model (str): Soniox TTS model to use. Defaults to "tts-rt-v1-prev

Create a new instance of Google GenAI LLM. Environment Requirements: - For VertexAI: Set the `GOOGLE_APPLICATION_CREDENTIALS

Create a new instance of Google STT. Credentials must be provided, either by using the ``credentials_info`` dict, or reading

Create a new instance of Gemini TTS. Environment Requirements: - For VertexAI: Set the `GOOGLE_APPLICATION_CREDENTIALS` envi

Initializes a RealtimeModel instance for interacting with Google's Realtime API. Environment Requirements: - For VertexAI: S

Create a new instance of Speechify TTS. Args: voice_id (NotGivenOr[str]): Voice ID. Defaults to `cliff`. enc

Create a new instance of Inworld STT. Args: api_key: Inworld API key. If not provided, reads from INWORLD_API_KEY env var.

Create a new instance of Gladia STT. Args: model: The model to use for recognition. Defaults to "solaria-1". interim_

Create a new instance of Speechmatics STT using the Voice SDK. Args: api_key: Speechmatics API key. Can be set via `api_key` argu

Create a new instance of Speechmatics TTS. Args: voice (str): Voice model to use for synthesis. Options: "sarah", "theo"

Initialize the Ultravox RealtimeModel. Parameters ---------- model_id : str | UltravoxModel The Ultravox model to

Create a new instance of Azure STT. Either ``speech_host`` or ``speech_key`` and ``speech_region`` or ``speech_auth_token``

Create a new instance of Fireworks AI STT. Args: model: The Fireworks AI STT model to use. Defaults to NOT_GIVEN (server

Create a new instance of OpenAI STT. Args: language: The language code to use for transcription (e.g., "en" for English)

Create a new instance of OpenAI Responses LLM. ``api_key`` must be set to your OpenAI API key, either using the argument or by setti

Args: base_url: The AssemblyAI streaming endpoint base URL. Use the EU endpoint (wss://streaming.eu.assemblyai.co

Create a new instance of Groq LLM. ``api_key`` must be set to your Groq API key, either using the argument or by setting the

Create a new instance of Groq TTS. if `api_key` is not provided, it will be read from the ``GROQ_API_KEY`` environmental var

Create a new instance of Async TTS. See https://docs.async.com/text-to-speech-websocket-3477526w0 for more details on th

Create a new instance of MistralAI STT. Args: client: Optional pre-configured MistralAI client instance. api

Create a new instance of MistralAI TTS. Args: client: Optional pre-configured MistralAI client instance. api

Simulate a long running task.

Advance the head by `self._step` dots along the loop of still-running cells. Distance per frame is the speed knob: raising it moves the head

Ask the user if they want to accept this job and forward the answer to the server. If we get the job assigned, we start a new process.

Return ``frame`` with ``gain`` applied, or the frame unchanged when ``gain`` is ``None`` (single source of truth for the no-op fast path).