# This file was auto-generated by Fern from our API Definition. import typing from contextlib import asynccontextmanager, contextmanager import httpx import websockets.exceptions import websockets.sync.client as websockets_sync_client from ..core.api_error import ApiError from ..core.client_wrapper import AsyncClientWrapper, SyncClientWrapper from ..core.request_options import RequestOptions from .socket_client import AsyncSpeechToTextStreamingSocketClient, SpeechToTextStreamingSocketClient from .types.speech_to_text_streaming_flush_signal import SpeechToTextStreamingFlushSignal from .types.speech_to_text_streaming_high_vad_sensitivity import SpeechToTextStreamingHighVadSensitivity from .types.speech_to_text_streaming_input_audio_codec import SpeechToTextStreamingInputAudioCodec from .types.speech_to_text_streaming_language_code import SpeechToTextStreamingLanguageCode from .types.speech_to_text_streaming_mode import SpeechToTextStreamingMode from .types.speech_to_text_streaming_model import SpeechToTextStreamingModel from .types.speech_to_text_streaming_vad_signals import SpeechToTextStreamingVadSignals try: from websockets.legacy.client import connect as websockets_client_connect # type: ignore except ImportError: from websockets import connect as websockets_client_connect # type: ignore class RawSpeechToTextStreamingClient: def __init__(self, *, client_wrapper: SyncClientWrapper): self._client_wrapper = client_wrapper @contextmanager def connect( self, *, language_code: SpeechToTextStreamingLanguageCode, model: typing.Optional[SpeechToTextStreamingModel] = None, mode: typing.Optional[SpeechToTextStreamingMode] = None, sample_rate: typing.Optional[str] = None, high_vad_sensitivity: typing.Optional[SpeechToTextStreamingHighVadSensitivity] = None, vad_signals: typing.Optional[SpeechToTextStreamingVadSignals] = None, flush_signal: typing.Optional[SpeechToTextStreamingFlushSignal] = None, input_audio_codec: typing.Optional[SpeechToTextStreamingInputAudioCodec] = None, api_subscription_key: typing.Optional[str] = None, request_options: typing.Optional[RequestOptions] = None, ) -> typing.Iterator[SpeechToTextStreamingSocketClient]: """ WebSocket channel for real-time speech to text streaming. **Note:** This API Reference page is provided for informational purposes only. The Try It playground may not provide the best experience for streaming audio. For optimal streaming performance, please use the SDK or implement your own WebSocket client. Parameters ---------- language_code : SpeechToTextStreamingLanguageCode Specifies the language of the input audio in BCP-47 format. **Available Options (saarika:v2.5):** - `unknown` (default): Use when the language is not known; the API will auto-detect. - `hi-IN`: Hindi - `bn-IN`: Bengali - `gu-IN`: Gujarati - `kn-IN`: Kannada - `ml-IN`: Malayalam - `mr-IN`: Marathi - `od-IN`: Odia - `pa-IN`: Punjabi - `ta-IN`: Tamil - `te-IN`: Telugu - `en-IN`: English **Additional Options (saaras:v3 only):** - `as-IN`: Assamese - `ur-IN`: Urdu - `ne-IN`: Nepali - `kok-IN`: Konkani - `ks-IN`: Kashmiri - `sd-IN`: Sindhi - `sa-IN`: Sanskrit - `sat-IN`: Santali - `mni-IN`: Manipuri - `brx-IN`: Bodo - `mai-IN`: Maithili - `doi-IN`: Dogri model : typing.Optional[SpeechToTextStreamingModel] Specifies the model to use for speech-to-text conversion. - **saarika:v2.5** (default): Transcribes audio in the spoken language. - **saaras:v3**: State-of-the-art model with flexible output formats. Supports multiple modes via the `mode` parameter: transcribe, translate, verbatim, translit, codemix. mode : typing.Optional[SpeechToTextStreamingMode] Mode of operation. **Only applicable when using saaras:v3 model.** Example audio: 'मेरा फोन नंबर है 9840950950' - **transcribe** (default): Standard transcription in the original language with proper formatting and number normalization. - Output: `मेरा फोन नंबर है 9840950950` - **translate**: Translates speech from any supported Indic language to English. - Output: `My phone number is 9840950950` - **verbatim**: Exact word-for-word transcription without normalization, preserving filler words and spoken numbers as-is. - Output: `मेरा फोन नंबर है नौ आठ चार zero नौ पांच zero नौ पांच zero` - **translit**: Romanization - Transliterates speech to Latin/Roman script only. - Output: `mera phone number hai 9840950950` - **codemix**: Code-mixed text with English words in English and Indic words in native script. - Output: `मेरा phone number है 9840950950` sample_rate : typing.Optional[str] Audio sample rate for the WebSocket connection. When specified as a connection parameter, only 16kHz and 8kHz are supported. 8kHz is only available via this connection parameter. If not specified, defaults to 16kHz. high_vad_sensitivity : typing.Optional[SpeechToTextStreamingHighVadSensitivity] Enable high VAD (Voice Activity Detection) sensitivity vad_signals : typing.Optional[SpeechToTextStreamingVadSignals] Enable VAD signals in response flush_signal : typing.Optional[SpeechToTextStreamingFlushSignal] Signal to flush the audio buffer and finalize transcription input_audio_codec : typing.Optional[SpeechToTextStreamingInputAudioCodec] Audio codec/format of the input stream. Use this when sending raw PCM audio. Supported values: wav, pcm_s16le, pcm_l16, pcm_raw. api_subscription_key : typing.Optional[str] API subscription key for authentication request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- SpeechToTextStreamingSocketClient """ ws_url = self._client_wrapper.get_environment().production + "/speech-to-text/ws" query_params = httpx.QueryParams() if language_code is not None: query_params = query_params.add("language-code", language_code) if model is not None: query_params = query_params.add("model", model) if mode is not None: query_params = query_params.add("mode", mode) if sample_rate is not None: query_params = query_params.add("sample_rate", sample_rate) if high_vad_sensitivity is not None: query_params = query_params.add("high_vad_sensitivity", high_vad_sensitivity) if vad_signals is not None: query_params = query_params.add("vad_signals", vad_signals) if flush_signal is not None: query_params = query_params.add("flush_signal", flush_signal) if input_audio_codec is not None: query_params = query_params.add("input_audio_codec", input_audio_codec) ws_url = ws_url + f"?{query_params}" headers = self._client_wrapper.get_headers() if api_subscription_key is not None: headers["Api-Subscription-Key"] = str(api_subscription_key) if request_options and "additional_headers" in request_options: headers.update(request_options["additional_headers"]) try: with websockets_sync_client.connect(ws_url, additional_headers=headers) as protocol: yield SpeechToTextStreamingSocketClient(websocket=protocol) except websockets.exceptions.InvalidStatusCode as exc: status_code: int = exc.status_code if status_code == 401: raise ApiError( status_code=status_code, headers=dict(headers), body="Websocket initialized with invalid credentials.", ) raise ApiError( status_code=status_code, headers=dict(headers), body="Unexpected error when initializing websocket connection.", ) class AsyncRawSpeechToTextStreamingClient: def __init__(self, *, client_wrapper: AsyncClientWrapper): self._client_wrapper = client_wrapper @asynccontextmanager async def connect( self, *, language_code: SpeechToTextStreamingLanguageCode, model: typing.Optional[SpeechToTextStreamingModel] = None, mode: typing.Optional[SpeechToTextStreamingMode] = None, sample_rate: typing.Optional[str] = None, high_vad_sensitivity: typing.Optional[SpeechToTextStreamingHighVadSensitivity] = None, vad_signals: typing.Optional[SpeechToTextStreamingVadSignals] = None, flush_signal: typing.Optional[SpeechToTextStreamingFlushSignal] = None, input_audio_codec: typing.Optional[SpeechToTextStreamingInputAudioCodec] = None, api_subscription_key: typing.Optional[str] = None, request_options: typing.Optional[RequestOptions] = None, ) -> typing.AsyncIterator[AsyncSpeechToTextStreamingSocketClient]: """ WebSocket channel for real-time speech to text streaming. **Note:** This API Reference page is provided for informational purposes only. The Try It playground may not provide the best experience for streaming audio. For optimal streaming performance, please use the SDK or implement your own WebSocket client. Parameters ---------- language_code : SpeechToTextStreamingLanguageCode Specifies the language of the input audio in BCP-47 format. **Available Options (saarika:v2.5):** - `unknown` (default): Use when the language is not known; the API will auto-detect. - `hi-IN`: Hindi - `bn-IN`: Bengali - `gu-IN`: Gujarati - `kn-IN`: Kannada - `ml-IN`: Malayalam - `mr-IN`: Marathi - `od-IN`: Odia - `pa-IN`: Punjabi - `ta-IN`: Tamil - `te-IN`: Telugu - `en-IN`: English **Additional Options (saaras:v3 only):** - `as-IN`: Assamese - `ur-IN`: Urdu - `ne-IN`: Nepali - `kok-IN`: Konkani - `ks-IN`: Kashmiri - `sd-IN`: Sindhi - `sa-IN`: Sanskrit - `sat-IN`: Santali - `mni-IN`: Manipuri - `brx-IN`: Bodo - `mai-IN`: Maithili - `doi-IN`: Dogri model : typing.Optional[SpeechToTextStreamingModel] Specifies the model to use for speech-to-text conversion. - **saarika:v2.5** (default): Transcribes audio in the spoken language. - **saaras:v3**: State-of-the-art model with flexible output formats. Supports multiple modes via the `mode` parameter: transcribe, translate, verbatim, translit, codemix. mode : typing.Optional[SpeechToTextStreamingMode] Mode of operation. **Only applicable when using saaras:v3 model.** Example audio: 'मेरा फोन नंबर है 9840950950' - **transcribe** (default): Standard transcription in the original language with proper formatting and number normalization. - Output: `मेरा फोन नंबर है 9840950950` - **translate**: Translates speech from any supported Indic language to English. - Output: `My phone number is 9840950950` - **verbatim**: Exact word-for-word transcription without normalization, preserving filler words and spoken numbers as-is. - Output: `मेरा फोन नंबर है नौ आठ चार zero नौ पांच zero नौ पांच zero` - **translit**: Romanization - Transliterates speech to Latin/Roman script only. - Output: `mera phone number hai 9840950950` - **codemix**: Code-mixed text with English words in English and Indic words in native script. - Output: `मेरा phone number है 9840950950` sample_rate : typing.Optional[str] Audio sample rate for the WebSocket connection. When specified as a connection parameter, only 16kHz and 8kHz are supported. 8kHz is only available via this connection parameter. If not specified, defaults to 16kHz. high_vad_sensitivity : typing.Optional[SpeechToTextStreamingHighVadSensitivity] Enable high VAD (Voice Activity Detection) sensitivity vad_signals : typing.Optional[SpeechToTextStreamingVadSignals] Enable VAD signals in response flush_signal : typing.Optional[SpeechToTextStreamingFlushSignal] Signal to flush the audio buffer and finalize transcription input_audio_codec : typing.Optional[SpeechToTextStreamingInputAudioCodec] Audio codec/format of the input stream. Use this when sending raw PCM audio. Supported values: wav, pcm_s16le, pcm_l16, pcm_raw. api_subscription_key : typing.Optional[str] API subscription key for authentication request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncSpeechToTextStreamingSocketClient """ ws_url = self._client_wrapper.get_environment().production + "/speech-to-text/ws" query_params = httpx.QueryParams() if language_code is not None: query_params = query_params.add("language-code", language_code) if model is not None: query_params = query_params.add("model", model) if mode is not None: query_params = query_params.add("mode", mode) if sample_rate is not None: query_params = query_params.add("sample_rate", sample_rate) if high_vad_sensitivity is not None: query_params = query_params.add("high_vad_sensitivity", high_vad_sensitivity) if vad_signals is not None: query_params = query_params.add("vad_signals", vad_signals) if flush_signal is not None: query_params = query_params.add("flush_signal", flush_signal) if input_audio_codec is not None: query_params = query_params.add("input_audio_codec", input_audio_codec) ws_url = ws_url + f"?{query_params}" headers = self._client_wrapper.get_headers() if api_subscription_key is not None: headers["Api-Subscription-Key"] = str(api_subscription_key) if request_options and "additional_headers" in request_options: headers.update(request_options["additional_headers"]) try: async with websockets_client_connect(ws_url, extra_headers=headers) as protocol: yield AsyncSpeechToTextStreamingSocketClient(websocket=protocol) except websockets.exceptions.InvalidStatusCode as exc: status_code: int = exc.status_code if status_code == 401: raise ApiError( status_code=status_code, headers=dict(headers), body="Websocket initialized with invalid credentials.", ) raise ApiError( status_code=status_code, headers=dict(headers), body="Unexpected error when initializing websocket connection.", )