Skip to main content
POST
/
eleven
/
stems
音轨分离
curl --request POST \
  --url https://api.mountsea.ai/eleven/stems \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "audioUrl": "https://example.com/song.mp3",
  "stemVariationId": "six_stems_v1",
  "outputFormat": "mp3_44100_128",
  "signWithC2pa": false
}
'
{
  "taskId": "<string>"
}
Separate audio into individual stems using ElevenLabs’ stem separation technology.
This is an async task. The response contains a taskId — use Get Task Status to poll for the stem download URLs.

​
Separation Modes

ModeDescriptionCost
two_stems_v1Vocals + Instrumental (2 tracks)0.5x generation cost
six_stems_v16 individual stems (default)1x generation cost
Use two_stems_v1 for simple vocal/instrumental separation at half the cost. Use six_stems_v1 when you need granular control over individual instruments.

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
​
audioUrl
string
required

要分离的音频文件 URL（服务端会先下载再上传至 ElevenLabs）

Example:

"https://example.com/song.mp3"

​
stemVariationId
enum<string>
default:six_stems_v1

音轨分离变体。two_stems_v1 = 人声+伴奏双轨（0.5× 生成费用），six_stems_v1 = 六轨分离（1× 生成费用）

Available options:
two_stems_v1,
six_stems_v1
​
outputFormat
enum<string>
default:mp3_44100_128

各音轨的输出格式，格式为 codec_sampleRate_bitrate

Available options:
mp3_22050_32,
mp3_24000_48,
mp3_44100_32,
mp3_44100_64,
mp3_44100_96,
mp3_44100_128,
mp3_44100_192,
pcm_8000,
pcm_16000,
pcm_22050,
pcm_24000,
pcm_32000,
pcm_44100,
pcm_48000,
ulaw_8000,
alaw_8000,
opus_48000_32,
opus_48000_64,
opus_48000_96,
opus_48000_128,
opus_48000_192
​
signWithC2pa
boolean
default:false

是否使用 C2PA 签名标记 AI 生成内容。仅适用于 MP3 输出格式

Response

200 - application/json

任务创建成功

​
taskId
string
required

任务 ID，用于后续查询结果