API 参考
Fish Audio Create-Voice
Clone a voice from one clean reference recording, with no training step.
01
概览
提交Create Voice请求,并直接使用同一响应返回的结果。
快速开始
- 创建 API Key,并将其设置为 RUNAPI_API_KEY。
- 发送与请求 Schema 匹配的 POST 请求。
- 从成功响应正文中读取结果。
端点
- 基础 URL
https://runapi.ai- API 版本
v1- 身份验证
Authorization: Bearer YOUR_API_TOKEN
02
支持的模型
打开模型页可查看当前价格、限流和商业使用详情。
03
JSON 请求体请求 Schema
只发送此端点声明的字段。
请求体2 个字段
namestring
必填
source_audio_urlstring
必填
04
HTTP 200成功响应
POST /api/v1/fish_audio/voices
响应 Schema
JSON
{
"properties": {
"voice": {
"properties": {
"name": {
"type": "string"
},
"state": {
"enum": [
"created",
"training",
"trained",
"failed"
],
"type": "string"
},
"voice_id": {
"type": "string"
}
},
"required": [
"voice_id",
"state"
],
"type": "object",
"unevaluatedProperties": false
}
},
"required": [
"voice"
],
"type": "object",
"unevaluatedProperties": false
}
响应示例
JSON
{
"voice": {
"name": "Studio Narrator",
"state": "trained",
"voice_id": "voice_reference_narrator"
}
}
05
HTTP 401错误
POST /api/v1/fish_audio/voices
响应 Schema
JSON
{
"properties": {
"error": {
"description": "Human-readable error message.",
"type": "string"
}
},
"required": [
"error"
],
"type": "object",
"unevaluatedProperties": false
}
响应示例
JSON
{
"error": "Authentication required"
}
06
HTTP 400错误
POST /api/v1/fish_audio/voices
响应 Schema
JSON
{
"oneOf": [
{
"properties": {
"error": {
"description": "Human-readable error message.",
"type": "string"
}
},
"required": [
"error"
],
"type": "object",
"unevaluatedProperties": false
},
{
"properties": {
"error": {
"description": "Human-readable validation summary.",
"type": "string"
},
"errors": {
"additionalProperties": {
"items": {
"type": "string"
},
"type": "array"
},
"description": "Validation messages keyed by public request field, with an array of human-readable strings for each field.",
"type": "object"
}
},
"required": [
"error",
"errors"
],
"type": "object",
"unevaluatedProperties": false
}
]
}
响应示例
JSON
{
"error": "Validation failed",
"errors": {
"name": [
"is required"
]
}
}
07
HTTP 402错误
POST /api/v1/fish_audio/voices
响应 Schema
JSON
{
"properties": {
"error": {
"description": "Human-readable error message.",
"type": "string"
}
},
"required": [
"error"
],
"type": "object",
"unevaluatedProperties": false
}
响应示例
JSON
{
"error": "Insufficient balance"
}
08
HTTP 429错误
POST /api/v1/fish_audio/voices
响应 Schema
JSON
{
"properties": {
"error": {
"description": "Human-readable error message.",
"type": "string"
}
},
"required": [
"error"
],
"type": "object",
"unevaluatedProperties": false
}
响应示例
JSON
{
"error": "API key credit limit exceeded"
}
09
HTTP 409错误
POST /api/v1/fish_audio/voices
响应 Schema
JSON
{
"properties": {
"error": {
"description": "Human-readable error message.",
"type": "string"
}
},
"required": [
"error"
],
"type": "object",
"unevaluatedProperties": false
}
响应示例
JSON
{
"error": "The request uses features that are not supported for the selected model"
}
10
HTTP 429错误
POST /api/v1/fish_audio/voices
响应 Schema
JSON
{
"properties": {
"error": {
"description": "Human-readable error message.",
"type": "string"
}
},
"required": [
"error"
],
"type": "object",
"unevaluatedProperties": false
}
响应示例
JSON
{
"error": "Rate limit reached. Please retry later."
}
11
HTTP 503错误
POST /api/v1/fish_audio/voices
响应 Schema
JSON
{
"properties": {
"error": {
"description": "Human-readable error message.",
"type": "string"
}
},
"required": [
"error"
],
"type": "object",
"unevaluatedProperties": false
}
响应示例
JSON
{
"error": "Service under maintenance, please try again later"
}
12
HTTP 504错误
POST /api/v1/fish_audio/voices
响应 Schema
JSON
{
"properties": {
"error": {
"description": "Human-readable error message.",
"type": "string"
}
},
"required": [
"error"
],
"type": "object",
"unevaluatedProperties": false
}
响应示例
JSON
{
"error": "The request timed out"
}
13
生成的代码示例
直接使用 cURL,或安装所用语言的 SDK。每个示例都会提交本参考中经过验证的请求。
安装
Shell
pip install runapi-fish-audio
PYTHON
import os
from runapi.fish_audio import FishAudioClient
client = FishAudioClient(api_key=os.environ["RUNAPI_API_KEY"])
result = client.create_voice.run(
name="Studio Narrator",
source_audio_url="https://cdn.runapi.ai/public/samples/voice.mp3"
)