Initiate a session
Initiate a live transcription job. Use the returned ws url to connect to the websocket and start sending audio chunks. Use the returned id and the GET /v2/live/:id endpoint to obtain the status and results.
Authorizations
Your personal Gladia API key
Body
The bit depth of the audio stream
8, 16, 24, 32 If true, messages will be sent to configured url.
Specify the callback configuration
The number of channels of the audio stream
1 < x < 8Custom metadata you can attach to this live transcription
The encoding format of the audio stream. Supported formats:
- PCM: 8, 16, 24, and 32 bits
- A-law: 8 bits
- μ-law: 8 bits
Note: No need to add WAV headers to raw audio as the API supports both formats.
wav/pcm, wav/alaw, wav/ulaw The endpointing duration in seconds. Endpointing is the duration of silence which will cause an utterance to be considered as finished
0.01 < x < 10Specify the language configuration
The maximum duration in seconds without endpointing. If endpointing is not detected after this duration, current utterance will be considered as finished
5 < x < 60Specify the websocket messages configuration
Specify the post-processing configuration
Specify the pre-processing configuration
Specify the realtime processing configuration
The sample rate of the audio stream
8000, 16000, 32000, 44100, 48000 Was this page helpful?