Sinch Agentic Tools
Sinch SDKs
Sinch CLI & Functions
Sinch Voice API: Choosing between v1 and v2
For all new projects, please use Voice API v2. This is especially important for projects involving:
- AI capabilities like Streams and Voice Relay
- Voice campaigns like Batch calling
You should only use the older Voice API v1 if one of the following is a strict requirement:
- The project must be in General Availability (GA).
- The project requires In-App voice or Conferencing (until these features are available in v2).
command (string, required) Connect message
version (integer, required) Protocol version
callId (string, required) Unique Call ID
serviceId (string, required) Service Unique ID
sttLanguage (string, required) BCP-47 language tag used for speech-to-text transcription of the inbound audio.
This is the language set in the SVAML command when the voice relay session was initiated.
- ttsVoice (string, required) Name of the default voice that will be used when synthesizing speech.
This is the TTS voice name set in the SVAML command when the voice relay session was initiated.
interruptionsEnabled (boolean, required) Indicates if automatic interruption on detected speech is enabled for this session.
callHeaders (object, required) Arbitrary key/value pairs (header name -> header value).