Cookie Preferences
We use cookies to personalize content and analyze traffic. See our Cookie Policy.
No audio yet. Submit the form to generate audio.
Explore different use cases and parameter configurations
Transparent pricing with no hidden fees. Pay as you go.
| Rule & Modality | Channel | Credits | Price (USD) | Official / Reference Price | Daily Savings |
|---|---|---|---|---|---|
Suno vocal-separation musicSuno | Starter | 1per run | $0.005 | - | - |
Complete guide to using Suno
Separate vocals from instrumentals in AI-generated music - extract clean vocal tracks or instrumental backing for remixing and production.
The Suno Vocal Separation API allows you to separate any Suno-generated song into its vocal and instrumental components. Using advanced AI audio separation technology, the API extracts clean vocal tracks and pure instrumental backing from mixed audio. This enables you to create karaoke versions, remix with different vocals, sample instrumental elements, or analyze and process vocals and music independently.
A clean audio file containing only the vocal elements from the song. Perfect for remixing, sampling, or creating acapella versions.
A pure instrumental version with all vocals removed. Use for karaoke, background music, or remixing with different vocals.
Advanced AI algorithms ensure clean separation with minimal artifacts. Both vocal and instrumental outputs maintain high audio quality.
Works directly with suno/v5 generated tracks using task ID and audio ID. No need to download and re-upload files.
Get both the isolated vocals and the instrumental backing in a single API call. Both tracks are time-aligned with the original.
Separated tracks are delivered in high-quality MP3 format, ready for immediate use in DAWs, video editors, or further processing.
Separate vocals from instrumentals in a few simple steps
First, generate a song using the suno/v5 API. Note the task ID from the response.
Query the task to get the result. Each task produces 2 audio variations. Choose the audio ID you want to separate.
Call the vocal separation API with the task ID and audio ID. The system handles the rest.
Retrieve both the isolated vocal track and the instrumental backing. Use for remixing, karaoke, or production.
Follow these guidelines for optimal vocal separation
Separation works best on songs with clear vocals. Instrumental-only tracks won't have meaningful vocal content to extract.
Songs with well-balanced vocals and instruments separate most cleanly. Heavily processed or distorted audio may have more artifacts.
Ensure the source song generation is fully complete before requesting separation. Query task status to confirm success.
Extract instrumental backing tracks from AI-generated songs for karaoke applications and sing-along experiences.
Isolate vocals to add new backing tracks, or use the instrumental for different vocal recordings.
Extract specific vocal phrases or instrumental elements for use as samples in new productions.
Analyze vocal and instrumental components separately for music education, transcription, or AI training.
Works seamlessly with suno/v5 generation. Generate music and separate in one unified API workflow.
Advanced separation AI delivers clean tracks with minimal artifacts and full frequency response.
Just provide task ID and audio ID - no file uploads or complex parameters needed.
All APIs require authentication via Bearer Token.
Authorization: Bearer
Use the SDK to create tasks, store the returned taskId, and retrieve results for Suno.
Install @apipass-dev/apipass-sdk before running these SDK examples.
1npm install @apipass-dev/apipass-sdk
2# or
3pnpm add @apipass-dev/apipass-sdk
4# or
5yarn add @apipass-dev/apipass-sdkKeep your API key in server-side environment variables. The SDK sends it as a Bearer token and adds JSON headers automatically.
client.jobs.createTaskCreate a new task to separate vocals and instrumentals from a Suno-generated song
Use this example to get started quickly with the selected SDK.
1import { Apipass } from "@apipass-dev/apipass-sdk";
2
3const client = new Apipass({
4 apiKey: process.env.APIPASS_API_KEY!,
5});
6
7const task = await client.jobs.createTask({
8 "model": "suno/vocal-separation",
9 "callBackUrl": "https://your-domain.com/api/callback",
10 "input": {
11 "taskId": "task_source_generate_xxx",
12 "audioId": "audio_xxx"
13 }
14});
15
16console.log(task.data.taskId);The API accepts a JSON payload with the following structure:
1{
2 "model": "suno/vocal-separation",
3 "callBackUrl": "string (optional)",
4 "input": {
5 "taskId": "string (required)",
6 "audioId": "string (required)"
7 },
8 "channel": "auto"
9}modelRequiredstringModel identifier for Suno vocal separation
"suno/vocal-separation"
callBackUrlOptionalstringURL to receive webhook notifications when separation completes
"https://your-domain.com/api/callback"
channelOptionalstringYou may specify the corresponding provider within APIPASS via the channel parameter; these providers handle the actual image and video generation tasks. APIPASS currently offers three provider options:
The default value for the channel parameter is auto. When enabled, APIPASS automatically allocates tasks across available providers based on real-time pricing and stability metrics to balance minimal cost and reliable performance. Retain the default auto value unless you have custom routing requirements.
Available options:
auto
Parameters for vocal separation:
input.taskIdRequiredstringThe ApiPass taskId returned by a completed suno/generate or suno/extend createTask call. Do not pass the upstream NextMusic provider task ID.
"task_abc123xyz"
input.audioIdRequiredstringThe audio ID from the completed source task result item.
"audio_001"
1{
2 "code": 200,
3 "message": "success",
4 "data": {
5 "taskId": "task_vocal_separation_xxx"
6 }
7}codeStatus code, 200 for success
messageResponse message
data.taskIdTask ID for querying separation status
When vocal separation completes, a POST request is sent to your callBackUrl
1{
2 "code": 200,
3 "data": {
4 "taskId": "task_sep_xyz789",
5 "state": "success",
6 "completeTime": 1755599720000,
7 "costTime": 30000,
8 "model": "suno/vocal-separation",
9 "resultJson": {
10 "data": [
11 {
12 "id": "vocals_001",
13 "audio_url": "https://cdn.apipass.dev/results/task_sep_xyz789_vocals.mp3",
14 "type": "vocals"
15 },
16 {
17 "id": "instrumental_001",
18 "audio_url": "https://cdn.apipass.dev/results/task_sep_xyz789_instrumental.mp3",
19 "type": "instrumental"
20 }
21 ]
22 }
23 },
24 "msg": "Vocal separation completed successfully."
25}1{
2 "code": 501,
3 "data": {
4 "taskId": "task_sep_xyz789",
5 "state": "fail",
6 "failCode": "SOURCE_TASK_NOT_FOUND",
7 "failMsg": "The source Suno task or audio track was not found upstream. Use the taskId of a completed suno/generate or suno/extend task and an audioId from its resultJson.data[].id."
8 },
9 "msg": "Vocal separation failed."
10}client.jobs.recordInfoQuery separation task status and retrieve results
Use this example to get started quickly with the selected SDK.
1import { Apipass } from "@apipass-dev/apipass-sdk";
2
3const client = new Apipass({
4 apiKey: process.env.APIPASS_API_KEY!,
5});
6
7const result = await client.jobs.recordInfo("task_sep_xyz789");
8
9console.log(result.data.state);
10console.log(result.data.resultJson);1{
2 "code": 200,
3 "data": {
4 "taskId": "task_sep_xyz789",
5 "state": "success",
6 "resultJson": {
7 "data": [
8 {
9 "id": "vocals_001",
10 "audio_url": "https://cdn.apipass.dev/results/task_sep_xyz789_vocals.mp3",
11 "type": "vocals"
12 },
13 {
14 "id": "instrumental_001",
15 "audio_url": "https://cdn.apipass.dev/results/task_sep_xyz789_instrumental.mp3",
16 "type": "instrumental"
17 }
18 ]
19 }
20 }
21}data.stateCurrent state: queuing, generating, success, or fail
data.resultJson.data[0]Isolated vocals track with type='vocals'
data.resultJson.data[1]Instrumental backing track with type='instrumental'
The API page shows the parameter schema, but Suno also has several business-specific mode combinations and callback rules that are easy to miss.
All APIs require authentication via Bearer Token.
Authorization: Bearer
Create a new task to separate vocals and instrumentals from a Suno-generated song
The API accepts a JSON payload with the following structure:
1{
2 "model": "suno/vocal-separation",
3 "callBackUrl": "string (optional)",
4 "input": {
5 "taskId": "string (required)",
6 "audioId": "string (required)"
7 },
8 "channel": "auto"
9}modelRequiredstringModel identifier for Suno vocal separation
"suno/vocal-separation"
callBackUrlOptionalstringURL to receive webhook notifications when separation completes
"https://your-domain.com/api/callback"
channelOptionalstringYou may specify the corresponding provider within APIPASS via the channel parameter; these providers handle the actual image and video generation tasks. APIPASS currently offers three provider options:
The default value for the channel parameter is auto. When enabled, APIPASS automatically allocates tasks across available providers based on real-time pricing and stability metrics to balance minimal cost and reliable performance. Retain the default auto value unless you have custom routing requirements.
Available options:
auto
Parameters for vocal separation:
input.taskIdRequiredstringThe ApiPass taskId returned by a completed suno/generate or suno/extend createTask call. Do not pass the upstream NextMusic provider task ID.
"task_abc123xyz"
input.audioIdRequiredstringThe audio ID from the completed source task result item.
"audio_001"
1curl -X POST "https://api.apipass.dev/api/v1/jobs/createTask" \
2 -H "Content-Type: application/json" \
3 -H "Authorization: Bearer YOUR_API_KEY" \
4 -d '{
5 "model": "suno/vocal-separation",
6 "callBackUrl": "https://your-domain.com/api/callback",
7 "input": {
8 "taskId": "task_source_generate_xxx",
9 "audioId": "audio_xxx"
10 }
11 }'1{
2 "code": 200,
3 "message": "success",
4 "data": {
5 "taskId": "task_vocal_separation_xxx"
6 }
7}codeStatus code, 200 for success
messageResponse message
data.taskIdTask ID for querying separation status
MiniMax
MiniMax
MiniMax Music 1.5 AI music generation model, supports lyrics and style prompt to generate music
Starting from
0 credits
Starting from
0 credits