通过统一接口调用 ElevenLabs 和 Minimax 语音合成服务,支持多语言、多音色的高质量 TTS。
所有请求需在 Header 中携带 Bearer Token:
Authorization: Bearer YOUR_API_KEY
/api/v1/audio/tts创建语音合成任务
/api/v1/audio/tts?task_id=xxx查询任务状态并获取音频链接
选择语音服务商查看对应的参数和示例
ElevenLabs 行业领先的文本转语音服务,超低延迟,支持 70+ 语言,表现力极强。
eleven-tts-flasheleven-tts-turboeleven-tts-multilingualeleven-tts-v321m00Tcm4TlvDq8ikWAMpNInz6obpgDQGcFmaJgBEXAVITQu4vr4xnSDxMaL# Step 1: Create TTS task
curl -X POST https://apimodels.app/api/v1/audio/tts \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "eleven-tts-v3",
"text": "Hello, this is a test of ElevenLabs text-to-speech.",
"voice_id": "21m00Tcm4TlvDq8ikWAM",
"language_code": "en"
}'
# Step 2: Poll status
curl "https://apimodels.app/api/v1/audio/tts?task_id=TASK_ID" \
-H "Authorization: Bearer YOUR_API_KEY"{
"code": 200,
"msg": "success",
"data": {
"taskId": "clxxx...",
"state": "pending"
}
}{
"code": 200,
"msg": "success",
"data": {
"taskId": "clxxx...",
"state": "completed",
"result": "https://cdn.example.com/audio.mp3",
"createTime": 1705123450000,
"completeTime": 1705123460000
}
}{
"code": 200,
"msg": "success",
"data": {
"taskId": "clxxx...",
"state": "failed",
"failMsg": "Invalid voice_id"
}
}在创建请求中传入 callback_url 后,任务进入 completed 或 failed 终态时,我们会向该地址发起一次 HTTP POST。请求头仅包含 Content-Type: application/json,无签名头。失败会自动重试 3 次(指数退避 1s/2s/4s,单次超时 10s);如果仍未成功,后台会在 30 分钟内继续补偿重发,直到接收端返回 2xx。
POST {your callback_url}
Content-Type: application/json
{
"code": 200,
"msg": "success",
"data": {
"taskId": "clxxx...",
"model": "<provider>/<model_name>",
"state": "completed" | "failed",
"param": "<JSON string>", // request params, JSON.parse once
"resultJson": "<JSON string> | null", // result object, JSON.parse once
"failCode": null | "string",
"failMsg": null | "string",
"costTime": 12345, // duration in ms
"completeTime": 1705123460000, // ms epoch
"createTime": 1705123450000 // ms epoch
}
}注意:data.param 与 data.resultJson 都是 JSON 字符串,使用前必须 JSON.parse 一次。
{
"resultUrls": ["https://r2.apimodels.app/audio/xxx.mp3"],
"audioDuration": 12.5 // optional, seconds
}resultUrls 是 R2 托管的音频 URL 数组,state=completed 时长度通常为 1。state=failed 时 resultJson 通常为 null 或 {"resultUrls":[]},请不要假设一定有音频链接。
app.post('/webhook/audio', express.json(), (req, res) => {
const { taskId, state, resultJson, failMsg } = req.body.data
if (state === 'completed') {
const r = JSON.parse(resultJson)
console.log('audio ready', taskId, r.resultUrls[0], r.audioDuration)
} else {
console.warn('audio failed', taskId, failMsg)
}
res.status(200).end() // must be 2xx, otherwise we retry
})pending任务已排队,等待处理processing语音合成中completed合成成功,可获取音频链接failed合成失败400请求参数错误或缺失401API 密钥无效402积分不足404任务 ID 不存在500服务器内部错误