Transcribe audio via SLNG’s native WebSocket protocol bridge. The model_variant path parameter specifies the target STT model (e.g., deepgram/nova:3, slng/openai/whisper:large-v3).
API key issued by SLNG. Pass as Authorization: Bearer <token>.
Target STT model. Must support WebSocket streaming with final_transcript.
deepgram/nova:2, deepgram/nova:3, deepgram/nova:3-medical, slng/deepgram/nova:3-en, slng/deepgram/nova:3-es, slng/deepgram/nova:3-hi, slng/deepgram/nova:3-multi, slng/openai/whisper:large-v3, slng/openai/whisper:large-v3-compressed Unmute STT request.
Audio file to transcribe.
Language code for recognition.
Audio sample rate in Hz.
8000, 16000, 22050, 24000, 32000, 48000 Audio encoding format.
linear16, mp3, opus Enable voice activity detection.
Enable partial transcription results.
Transcription successful.