fish_audio_tts
Convert text to speech using the Fish Audio TTS API, with options for voice models, streaming, and audio formats.
Instructions
Generate speech from text using Fish Audio TTS API
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| auto_play | No | Automatically play the generated audio (optional) | |
| format | No | Output audio format (optional) | mp3 |
| latency | No | Latency mode (optional) | balanced |
| mp3_bitrate | No | MP3 bitrate in kbps (optional) | |
| normalize | No | Enable text normalization (optional) | |
| output_path | No | Custom output file path (optional) | |
| realtime_play | No | Enable real-time audio playback during streaming (optional) | |
| reference_id | No | Voice model reference ID (optional) | |
| reference_name | No | Voice model name to search for (optional) | |
| reference_tag | No | Voice model tag to search for (optional) | |
| streaming | No | Enable HTTP streaming mode (optional) | |
| text | Yes | Text to convert to speech | |
| websocket_streaming | No | Enable WebSocket streaming mode (optional) |
Input Schema (JSON Schema)
{
"properties": {
"auto_play": {
"default": false,
"description": "Automatically play the generated audio (optional)",
"type": "boolean"
},
"format": {
"default": "mp3",
"description": "Output audio format (optional)",
"enum": [
"mp3",
"wav",
"pcm",
"opus"
],
"type": "string"
},
"latency": {
"default": "balanced",
"description": "Latency mode (optional)",
"enum": [
"normal",
"balanced"
],
"type": "string"
},
"mp3_bitrate": {
"default": 128,
"description": "MP3 bitrate in kbps (optional)",
"enum": [
64,
128,
192
],
"type": "number"
},
"normalize": {
"default": true,
"description": "Enable text normalization (optional)",
"type": "boolean"
},
"output_path": {
"description": "Custom output file path (optional)",
"type": "string"
},
"realtime_play": {
"default": false,
"description": "Enable real-time audio playback during streaming (optional)",
"type": "boolean"
},
"reference_id": {
"description": "Voice model reference ID (optional)",
"type": "string"
},
"reference_name": {
"description": "Voice model name to search for (optional)",
"type": "string"
},
"reference_tag": {
"description": "Voice model tag to search for (optional)",
"type": "string"
},
"streaming": {
"default": false,
"description": "Enable HTTP streaming mode (optional)",
"type": "boolean"
},
"text": {
"description": "Text to convert to speech",
"maxLength": 10000,
"type": "string"
},
"websocket_streaming": {
"default": false,
"description": "Enable WebSocket streaming mode (optional)",
"type": "boolean"
}
},
"required": [
"text"
],
"type": "object"
}