Text to Speech

Convert text to speech. Supports voice model IDs, zero-shot cloning, multi-speaker dialogue, and control of speed, volume, and output format.

Synchronous endpoint: the request returns an audio binary stream with no task polling. Only application/json and application/msgpack are accepted. For best results, upload a reference voice before calling this endpoint to improve quality and reduce latency. Inline reference audio (references) requires MessagePack; JSON cannot carry binary data.

Base URL

• https://api.autorouter.top — Production

Authentication

BearerAuth: http (bearer) Authenticate using a Bearer Token. Format: Authorization: Bearer sk-xxxxxx

Endpoints

POST /fishaudio/v1/tts

Create a text-to-speech request

Send text and a voice; the response is an audio stream. Multi-speaker dialogue is supported only by the S2 series (s2-pro, s2.1-pro, s2.1-pro-free) and drama-3-preview, not s1.

Headers

Request Body

Content-Type: application/json

Example (single speaker):

{
  "text": "Hello! Welcome to Fish Audio.",
  "reference_id": "model-id",
  "temperature": 0.7,
  "top_p": 0.7,
  "prosody": {
    "speed": 1,
    "volume": 0,
    "normalize_loudness": true
  },
  "chunk_length": 300,
  "normalize": true,
  "format": "mp3",
  "sample_rate": 44100,
  "mp3_bitrate": 128,
  "latency": "normal",
  "max_new_tokens": 1024,
  "repetition_penalty": 1.2,
  "min_chunk_length": 50,
  "condition_on_previous_chunks": true,
  "early_stop_threshold": 1
}

Example (multi-speaker, S2 family only):

{
  "text": "<|speaker:0|>Hello!<|speaker:1|>Hi there!",
  "reference_id": ["speaker-a-id", "speaker-b-id"]
}

Properties:

Responses

200: Synthesis succeeded; audio stream returned

Content-Type: audio type depending on format (for example audio/mpeg)

401: Unauthorized

Content-Type: application/json

402: Insufficient balance

Content-Type: application/json

503: Service overloaded

Content-Type: application/json

Request Example

curl -X POST "https://api.autorouter.top/fishaudio/v1/tts" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxxx" \
  -H "model: s2.1-pro" \
  --output speech.mp3 \
  -d '{
  "text": "Hello! Welcome to Fish Audio.",
  "reference_id": "model-id",
  "format": "mp3",
  "sample_rate": 44100,
  "mp3_bitrate": 128,
  "latency": "normal"
}'

Response Example

<binary audio stream>

Response fields:

Error Handling

HTTP 401 / 403 Auth Errors

• 401 Unauthorized: API Key invalid or expired
• 403 Forbidden: API Key has no access to this model (check token's model allowlist)

HTTP 402 Insufficient Balance

Returns insufficient user quota. Top up at the AutoRouter console.

HTTP 503 Service Overloaded

The server is under too much load to process the request. Retry later.