Skip to main content
WSS
/
v1
/
tts
/
sarvam
/
bulbul:v3
Messages
bearer
type:http

API key issued by SLNG. Pass as Authorization: Bearer <token> in the WebSocket upgrade request headers.

method
type:string

GET

allOf
type:allOf

Must contain all of these types

Init Request
type:object

Initialize a TTS session with model and voice configuration.

Text Message
type:object

Send text to synthesize into audio output.

Flush Message
type:object

Force any buffered text/audio to be finalized and delivered.

Clear Message
type:object

Clear any queued text/audio from the current session.

Cancel Message
type:object

Cancel the current generation and stop any further audio.

Ready Response
type:object

Indicates the session is ready to receive messages.

Audio Chunk
type:object

Chunk of base64-encoded audio data.

Segment Start
type:object

Signals the start of a synthesized segment.

Segment End
type:object

Signals the end of a synthesized segment.

Flushed
type:object

Acknowledges that buffered output was flushed.

Cleared
type:object

Acknowledges that queued output was cleared.

Audio End
type:object

Signals the end of audio generation.

Error Response
type:object

Indicates an error occurred during synthesis.