API ReferenceText to Speech
TTS Models
Review the supported modelId values, model characteristics, and selection guidance for text to speech.
TTS Models
Use modelId to select the TTS engine and version, and use voiceId to select the speaker. Send both fields in sync and async TTS requests so the generation and billing model are explicit.
Supported modelId values
modelId | Brand | Version | Best suited for |
|---|---|---|---|
fishaudio-s21pro | Fish Audio | S2.1 Pro | Higher-quality production generation |
fishaudio-s21pro-flash | Fish Audio | S2.1 Pro Flash | Default; faster with lower credit consumption |
fishaudio-s2pro | Fish Audio | S2 Pro | Workflows that target S2 Pro |
fishaudio-s1 | Fish Audio | S1 | Existing integrations that still depend on S1 |
minimax-2.8-turbo | MiniMax | Speech 2.8 Turbo | Default MiniMax option focused on speed |
minimax-2.8-hd | MiniMax | Speech 2.8 HD | Higher-quality MiniMax output |
minimax-2.6-turbo | MiniMax | Speech 2.6 Turbo | Compatibility with 2.6 Turbo workflows |
minimax-2.6-hd | MiniMax | Speech 2.6 HD | Compatibility with 2.6 HD workflows |
qwen3-tts-flash | Qwen | TTS 3 Flash | Fast generation with Qwen voices |
Treat the TTS schema returned by GET /api/openapi.json as the source of truth. It reflects the current public contract when model availability, account access, or brand capabilities change.
Choosing a model
- Choose a
modelIdfrom the same brand as the selectedvoiceId. For example, use afishaudio-*model with a Fish Audio voice. - Fish Audio defaults to
fishaudio-s21pro-flashwhenmodelIdis omitted. - MiniMax defaults to
minimax-2.8-turbo, and Qwen defaults toqwen3-tts-flash. - Models can differ in quality, latency, expression, and credit consumption. Test a short sample before starting a large batch.
Request example
Sync and async TTS requests both use modelId:
{
"text": "Hello, this is a TTS model test.",
"voiceId": "00a1b221-6137-4b73-ad62-b0cbce134167",
"modelId": "fishaudio-s21pro-flash",
"format": "mp3",
"speed": 1
}Endpoint mapping
| Endpoint | Model field |
|---|---|
POST /api/open/v1/speech/tts | modelId |
POST /api/open/v1/speech/tts/jobs | modelId |
OpenAI-compatible POST /v1/audio/speech | model |
Continue with Sync HTTP, Async Jobs, or OpenAI-Compatible TTS for complete request details.