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.
Enable high VAD (Voice Activity Detection) sensitivity
VAD probability threshold (0.0–1.0) above which a frame is considered speech. Overrides the server default when provided.
VAD probability threshold (0.0–1.0) below which a frame is considered silence. Overrides the server default (or the high_vad_sensitivity preset) when provided.
Number of negative (silence) frames needed within the window to end a speech segment. Overrides the server default (or the high_vad_sensitivity preset) when provided.
Sliding window size (in frames) over which negative frames are counted. Overrides the server default (or the high_vad_sensitivity preset) when provided.
Volume level (dB) below which audio is considered too quiet to be speech. When not provided, no volume-based filtering is applied.
Minimum speech frames required to register a barge-in / interruption. Overrides the server default when provided.
Audio codec/format of the input stream. Use this when sending raw PCM audio. Supported values: wav, pcm_s16le, pcm_l16, pcm_raw.
Send audio data for real-time speech to text streaming
Receive real-time transcription results from the WebSocket
Specifies the language of the input audio in BCP-47 format.
Available Options (saarika:v2.5, legacy):
unknown (default): Use when the language is not known; the API will auto-detect.hi-IN: Hindibn-IN: Bengaligu-IN: Gujaratikn-IN: Kannadaml-IN: Malayalammr-IN: Marathiod-IN: Odiapa-IN: Punjabita-IN: Tamilte-IN: Teluguen-IN: EnglishAdditional Options (saaras:v3, recommended):
as-IN: Assameseur-IN: Urdune-IN: Nepalikok-IN: Konkaniks-IN: Kashmirisd-IN: Sindhisa-IN: Sanskritsat-IN: Santalimni-IN: Manipuribrx-IN: Bodomai-IN: Maithilidoi-IN: DogriSpecifies the model to use for speech-to-text conversion.
saaras:v3 (default, recommended): State-of-the-art model with flexible output formats. Supports multiple modes via the mode parameter: transcribe, translate, verbatim, translit, codemix.
saarika:v2.5 (legacy): Transcribes audio in the spoken language. Kept for backward compatibility.
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.
मेरा फोन नंबर है 9840950950translate: Translates speech from any supported Indic language to English.
My phone number is 9840950950verbatim: Exact word-for-word transcription without normalization, preserving filler words and spoken numbers as-is.
मेरा फोन नंबर है नौ आठ चार zero नौ पांच zero नौ पांच zerotranslit: Romanization - Transliterates speech to Latin/Roman script only.
mera phone number hai 9840950950codemix: Code-mixed text with English words in English and Indic words in native script.
मेरा phone number है 9840950950