Streaming Speech-to-Text
HandshakeTry it
GET
wss://api.assemblyai.com/v2/realtime/ws
Headers
Authorization
Authenticate using your AssemblyAI API key
Query parameters
sample_rate
The sample rate of the streamed audio
word_boost
Add up to 2500 characters of custom vocabulary. The parameter value must be a JSON encoded array of strings. The JSON must be URL encoded like other query string parameters.
encoding
The encoding of the audio data
Allowed values:
token
Authenticate using a generated temporary token
disable_partial_transcripts
Set to true to not receive partial transcripts. Defaults to false.
enable_extra_session_information
Set to true to receive the SessionInformation message before the session ends. Defaults to false.
Send
Audio Data
OR
Terminate Session
OR
Force End Utterance
OR
Configure End Utterance Silence Threshold
Receive
Session Begins
OR
Partial Transcript
OR
Final Transcript
OR
Session Information
OR
Session Terminated
OR
Realtime Error