Real-time speech-to-text transcription with ultra-low latency using Deepgram's Nova model. Optimized for streaming audio with intelligent Voice Activity Detection (VAD) and speaker diarization.
nova:3-medical - websocket
Speech-to-Text API for converting audio files to text using Deepgram nova. Real-time speech-to-text transcription with ultra-low latency using Deepgram's Nova model. Optimized for streaming audio with intelligent Voice Activity Detection (VAD) and speaker diarization.
Headers
AuthorizationThe Authorization header is used to authenticate with the API using your API key. Value is of the format Bearer YOUR_KEY_HERE.
UpgradeConnectionnova:3-medical - websocket › Responses
Switching Protocols
nova:3-medical - http
Speech-to-Text API for converting audio files to text using Deepgram nova. Real-time speech-to-text transcription with ultra-low latency using Deepgram's Nova model. Optimized for streaming audio with intelligent Voice Activity Detection (VAD) and speaker diarization.
Headers
AuthorizationThe Authorization header is used to authenticate with the API using your API key. Value is of the format Bearer YOUR_KEY_HERE.
nova:3-medical - http › Request Body
audioAudio file to transcribe. Supported formats: mp3, mp4, mpeg, mpga, m4a, wav, webm. Maximum file size: 25MB.
languageOptional: ISO-639-1 language code (e.g., 'en', 'es', 'fr', 'de'). If not specified, the model will auto-detect the language. Providing the language can improve accuracy and reduce processing time.
nova:3-medical - http › Responses
Successful transcription
textThe transcribed text
languageDetected or specified language code
durationDuration of the audio file in seconds
confidenceAverage confidence score for the transcription (0.0 to 1.0)