模型市场支持← 返回应用

ElevenLabs

ElevenLabs 模型通过一个统一的异步任务 API 调用。用 POST /api/generate 发起任务，再轮询 GET /api/generate/{taskId} 直到完成。本系列提供 4 个端点。

概览

每个端点共享相同的外层结构 —— 只有 model 和 input 字段不同。可在模型市场的 playground 中运行任意一个。

认证

在 /api-keys 创建 API 密钥，然后作为 Bearer token 发送。已登录时从浏览器发起的请求也可通过会话 cookie 生效。

Authorization: Bearer <YOUR_API_KEY>

创建任务

POST
POST https://api.lithovas.com/api/generate

请求体：{ "model": "<slug>", "input": { … } }

响应：{ "taskId": "<id>", "state": "waiting" }

查询结果

GET
GET https://api.lithovas.com/api/generate/<taskId>

响应：{ "taskId", "state": "waiting" | "success" | "fail", "resultUrls": [ … ], "creditsConsumed", "failMsg", "balance" }

异步
创建任务返回 200 只表示任务已被接受 —— 并非已完成。请轮询此端点，直到 state 变为 success 或 fail。失败任务不计费。

端点

模型任务model slug
Audio IsolationAudio to Audioelevenlabs/audio-isolation
Text To Dialogue V3Text to Speechelevenlabs/text-to-dialogue-v3
Text To Speech Multilingual V2Text to Speechelevenlabs/text-to-speech-multilingual-v2
Text To Speech Turbo 2.5Text to Speechelevenlabs/text-to-speech-turbo-2-5

Audio Isolation · Audio to Audio

POSTAudio to Audioelevenlabs/audio-isolation
input 字段
audio_urlstring必填

URL of audio to isolate voice from (mp3/wav/aac/mp4/ogg, max 10MB)

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "elevenlabs/audio-isolation",
  "input": {
    "audio_url": "https://example.com/reference.mp3"
  }
}'

Text To Dialogue V3 · Text to Speech

POSTText to Speechelevenlabs/text-to-dialogue-v3
input 字段
dialoguearray<object>必填

Array of dialogue items with text and voice; combined text <=5000 chars

dialogue[].textstring必填

Dialogue text content for speech generation

dialogue[].voiceenum<string>必填

Voice ID or preset name for speech synthesis (60 voice IDs)

stabilitynumber可选

Voice stability parameter controlling consistency

language_codestring可选

Language code (50+ codes); omit for automatic detection

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "elevenlabs/text-to-dialogue-v3",
  "input": {
    "dialogue": [],
    "dialogue[].text": "example",
    "dialogue[].voice": "example",
    "stability": 0.5,
    "language_code": "example"
  }
}'

Text To Speech Multilingual V2 · Text to Speech

POSTText to Speechelevenlabs/text-to-speech-multilingual-v2
input 字段
textstring必填

Text to convert to speech (max 5000 characters)

voicestring必填

Voice ID or preset name for speech generation (59 voice IDs)

stabilitynumber可选

Voice stability control (0-1, step 0.01)

similarity_boostnumber可选

Similarity boost parameter (0-1, step 0.01)

stylenumber可选

Style exaggeration level (0-1, step 0.01)

speednumber可选

Speech speed multiplier (0.7-1.2, step 0.01)

timestampsboolean可选

Return word-level timestamps in output

previous_textstring可选

Prior context text for continuity (max 5000 chars)

next_textstring可选

Following context text for continuity (max 5000 chars)

language_codestring可选

ISO 639-1 language code for enforcement (max 500 chars)

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "elevenlabs/text-to-speech-multilingual-v2",
  "input": {
    "text": "example",
    "voice": "example",
    "stability": 0.5,
    "similarity_boost": 0.75,
    "style": 0,
    "speed": 1,
    "timestamps": false,
    "previous_text": "example",
    "next_text": "example",
    "language_code": "example"
  }
}'

Text To Speech Turbo 2.5 · Text to Speech

POSTText to Speechelevenlabs/text-to-speech-turbo-2-5
input 字段
textstring必填

Text to convert to speech (max 5000 characters)

voicestring可选

Voice ID or preset name for speech generation (60+ voice IDs)

stabilitynumber可选

Voice stability parameter (0-1, step 0.01)

similarity_boostnumber可选

Similarity boost parameter (0-1, step 0.01)

stylenumber可选

Style exaggeration level (0-1, step 0.01)

speednumber可选

Speech speed multiplier (0.7-1.2, step 0.01)

timestampsboolean可选

Return word-level timing information

previous_textstring可选

Prior context text for continuity (max 5000 chars)

next_textstring可选

Following context text for continuity (max 5000 chars)

language_codestring可选

ISO 639-1 language code for enforcement

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "elevenlabs/text-to-speech-turbo-2-5",
  "input": {
    "text": "example",
    "voice": "EkK5I93UQWFDigLMpZcX",
    "stability": 0.5,
    "similarity_boost": 0.75,
    "style": 0,
    "speed": 1,
    "timestamps": false,
    "previous_text": "example",
    "next_text": "example",
    "language_code": "example"
  }
}'