Messages
{
"event": "start",
"request": {
"reference_id": "9a9cf47702da476aa4629e2506d4a857",
"format": "mp3"
}
}{
"event": "text",
"text": "Hello from Fish Audio."
}{
"event": "flush"
}{
"event": "stop"
}{
"event": "audio",
"audio": "<binary>"
}{
"event": "finish",
"reason": "stop"
}{
"event": "error",
"error": "Synthesis failed"
}Fish Audio TTS S2.1 Pro
Fish Audio TTS S2.1 Pro
Stream speech synthesis from Fish Speech S2.1 Pro over a native MessagePack WebSocket. Send a start frame followed by text frames; receive binary audio chunks.
WSS
/
v1
/
tts
/
fish
/
tts:s2.1-pro
Messages
{
"event": "start",
"request": {
"reference_id": "9a9cf47702da476aa4629e2506d4a857",
"format": "mp3"
}
}{
"event": "text",
"text": "Hello from Fish Audio."
}{
"event": "flush"
}{
"event": "stop"
}{
"event": "audio",
"audio": "<binary>"
}{
"event": "finish",
"reason": "stop"
}{
"event": "error",
"error": "Synthesis failed"
}bearer
type:http
API key issued by SLNG. Pass as Authorization: Bearer <token> in the WebSocket upgrade request headers.
method
type:string
GET
headers
type:object
X-World-Part-Override
type:enum
Target world part override. Auto-selected if not provided. Available world parts: eu.
Available options:
euStart Request
type:object
Open a Fish Audio synthesis session with voice and audio configuration.
Text Frame
type:object
Append text to synthesize on the active session.
Flush Frame
type:object
Force synthesis of buffered text without ending the session.
Stop Frame
type:object
End input; the server finishes synthesis and closes the session.
Audio Chunk
type:object
Streamed binary audio chunk from Fish Audio.
Finish
type:object
End-of-synthesis signal for the session.
Error
type:object
Error frame from the provider.
Was this page helpful?
⌘I