eachlabs-music

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

EachLabs Music

EachLabs 音乐服务

Generate songs, instrumentals, lyrics, podcasts, and more using Mureka AI models via the EachLabs Predictions API.

通过EachLabs Predictions API，借助Mureka AI模型生成歌曲、器乐、歌词、播客及更多音频内容。

Authentication

身份验证

Header: X-API-Key: <your-api-key>

Set the

EACHLABS_API_KEY

environment variable. Get your key at eachlabs.ai.

Header: X-API-Key: <your-api-key>

设置

EACHLABS_API_KEY

环境变量。可前往eachlabs.ai获取您的API密钥。

Available Capabilities

可用功能

Mureka Models

Mureka模型

Capability	Slug	Description
Generate Song	`mureka-generate-song`	Create a full song with vocals from a prompt
Generate Instrumental	`mureka-generate-instrumental`	Create instrumental tracks
Generate Lyrics	`mureka-generate-lyrics`	Generate lyrics from a prompt
Extend Lyrics	`mureka-extend-lyrics`	Continue/extend existing lyrics
Extend Song	`mureka-extend-song`	Continue an existing song
Create Speech	`mureka-create-speech`	Generate speech audio
Create Podcast	`mureka-create-podcast`	Generate multi-speaker podcast
Recognize Song	`mureka-recognize-song`	Identify a song from audio
Describe Song	`mureka-describe-song`	Analyze and describe a song
Stem Song	`mureka-stem-song`	Separate audio into stems
Upload File	`mureka-upload-file`	Upload audio for other operations

功能	Slug	说明
生成歌曲	`mureka-generate-song`	根据提示生成带有人声的完整歌曲
生成器乐	`mureka-generate-instrumental`	创作器乐曲目
生成歌词	`mureka-generate-lyrics`	根据提示生成歌词
扩展歌词	`mureka-extend-lyrics`	续写/扩展现有歌词
扩展歌曲	`mureka-extend-song`	续写现有歌曲
生成语音	`mureka-create-speech`	生成语音音频
生成播客	`mureka-create-podcast`	生成多主播播客内容
歌曲识别	`mureka-recognize-song`	通过音频识别歌曲
歌曲描述	`mureka-describe-song`	分析并描述歌曲内容
音轨分离	`mureka-stem-song`	将音频分离为独立音轨
文件上传	`mureka-upload-file`	上传音频用于其他操作

Minimax Music

Minimax音乐

Capability	Slug	Description
Music v2	`minimax-music-v2`	Latest Minimax music generation
Music v1.5	`minimax-music-v1-5`	Stable Minimax music generation

功能	Slug	说明
Music v2	`minimax-music-v2`	最新版Minimax音乐生成模型
Music v1.5	`minimax-music-v1-5`	稳定版Minimax音乐生成模型

Prediction Flow

预测流程

Check model
```
GET https://api.eachlabs.ai/v1/model?slug=<slug>
```
— validates the model exists and returns the
```
request_schema
```
with exact input parameters. Always do this before creating a prediction to ensure correct inputs.
POST
```
https://api.eachlabs.ai/v1/prediction
```
with model slug, version
```
"0.0.1"
```
, and input matching the schema

Poll

GET https://api.eachlabs.ai/v1/prediction/{id}

until status is

"success"

"failed"

Extract the output from the response

检查模型
```
GET https://api.eachlabs.ai/v1/model?slug=<slug>
```
— 验证模型是否存在，并返回包含精确输入参数的
```
request_schema
```
。在创建预测前务必执行此步骤，以确保输入参数正确。
发送POST请求 至
```
https://api.eachlabs.ai/v1/prediction
```
，携带模型slug、版本
```
"0.0.1"
```
及符合schema的输入参数

轮询请求

GET https://api.eachlabs.ai/v1/prediction/{id}

，直到状态变为

"success"

或

"failed"

提取结果 从响应中获取输出内容

Examples

示例

Generate a Song

生成歌曲

bash

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "mureka-generate-song",
    "version": "0.0.1",
    "input": {
      "prompt": "An upbeat indie pop song about summer road trips with catchy chorus",
      "duration": 120
    }
  }'

bash

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{\n    "model": "mureka-generate-song",\n    "version": "0.0.1",\n    "input": {\n      "prompt": "An upbeat indie pop song about summer road trips with catchy chorus",\n      "duration": 120\n    }\n  }'

Generate Instrumental

生成器乐

bash

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "mureka-generate-instrumental",
    "version": "0.0.1",
    "input": {
      "prompt": "Lo-fi hip hop beat with jazzy piano chords and vinyl crackle, relaxing study music"
    }
  }'

bash

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{\n    "model": "mureka-generate-instrumental",\n    "version": "0.0.1",\n    "input": {\n      "prompt": "Lo-fi hip hop beat with jazzy piano chords and vinyl crackle, relaxing study music"\n    }\n  }'

Generate Lyrics

生成歌词

bash

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "mureka-generate-lyrics",
    "version": "0.0.1",
    "input": {
      "prompt": "Write lyrics for a heartfelt country ballad about coming home"
    }
  }'

bash

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{\n    "model": "mureka-generate-lyrics",\n    "version": "0.0.1",\n    "input": {\n      "prompt": "Write lyrics for a heartfelt country ballad about coming home"\n    }\n  }'

Create a Podcast

创建播客

bash

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "mureka-create-podcast",
    "version": "0.0.1",
    "input": {
      "prompt": "A 5-minute podcast discussion about the future of AI in music production",
      "speakers": ["Luna", "Jake"]
    }
  }'

bash

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{\n    "model": "mureka-create-podcast",\n    "version": "0.0.1",\n    "input": {\n      "prompt": "A 5-minute podcast discussion about the future of AI in music production",\n      "speakers": ["Luna", "Jake"]\n    }\n  }'

Extend an Existing Song

扩展现有歌曲

First upload the song, then extend it:

bash

undefined

先上传歌曲，再进行扩展：

bash

undefined

Step 1: Upload the audio file

curl -X POST https://api.eachlabs.ai/v1/prediction
-H "Content-Type: application/json"
-H "X-API-Key: $EACHLABS_API_KEY"
-d '{ "model": "mureka-upload-file", "version": "0.0.1", "input": { "file": "https://example.com/my-song.mp3", "purpose": "audio" } }'

curl -X POST https://api.eachlabs.ai/v1/prediction
-H "Content-Type: application/json"
-H "X-API-Key: $EACHLABS_API_KEY"
-d '{\n "model": "mureka-upload-file",\n "version": "0.0.1",\n "input": {\n "file": "https://example.com/my-song.mp3",\n "purpose": "audio"\n }\n }'

Step 2: Use the upload ID to extend the song

curl -X POST https://api.eachlabs.ai/v1/prediction
-H "Content-Type: application/json"
-H "X-API-Key: $EACHLABS_API_KEY"
-d '{ "model": "mureka-extend-song", "version": "0.0.1", "input": { "upload_audio_id": "<upload-id-from-step-1>", "prompt": "Continue with an energetic guitar solo bridge" } }'

undefined

curl -X POST https://api.eachlabs.ai/v1/prediction
-H "Content-Type: application/json"
-H "X-API-Key: $EACHLABS_API_KEY"
-d '{\n "model": "mureka-extend-song",\n "version": "0.0.1",\n "input": {\n "upload_audio_id": "<upload-id-from-step-1>",\n "prompt": "Continue with an energetic guitar solo bridge"\n }\n }'

undefined

Separate Audio Stems

分离音频音轨

bash

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "mureka-stem-song",
    "version": "0.0.1",
    "input": {
      "url": "https://example.com/song.mp3"
    }
  }'

bash

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{\n    "model": "mureka-stem-song",\n    "version": "0.0.1",\n    "input": {\n      "url": "https://example.com/song.mp3"\n    }\n  }'

Prompt Tips

提示词技巧

Specify genre: "indie pop", "lo-fi hip hop", "classical orchestral", "EDM"
Include mood: "upbeat", "melancholic", "energetic", "relaxing"
Mention instruments: "acoustic guitar", "piano", "synthesizer", "drums"
Describe tempo: "slow ballad", "fast-paced", "medium tempo groove"
For lyrics, mention theme and structure: "verse-chorus-verse about..."

明确音乐风格：如"indie pop"、"lo-fi hip hop"、"古典管弦乐"、"EDM"
标注情绪氛围：如"欢快"、"忧郁"、"充满活力"、"舒缓放松"
提及乐器类型：如"原声吉他"、"钢琴"、"合成器"、"架子鼓"
描述节奏速度：如"慢板民谣"、"快节奏"、"中等节奏律动"
针对歌词创作，需明确主题和结构：如"主歌-副歌-主歌，主题为……"

Parameter Reference

参数参考

See references/MODELS.md for complete parameter details for each model.

如需了解各模型的完整参数详情，请查看references/MODELS.md。