> ## Documentation Index > Fetch the complete documentation index at: https://docs.goenhance.ai/llms.txt > Use this file to discover all available pages before exploring further. # Vocal Remover > Separate any audio into two tracks: the **vocals** and everything else (the **instrumental**: music, beats and sound effects). Works on songs, podcasts, voice-overs over background music, and videos with sound (the first audio track is used). - One request always returns both tracks. - The billed length is the length of `audio_url`, measured before the task is accepted. **Pricing**: 0.1 tokens ($0.002) per minute of audio, rounded up to the whole minute. A 61-second file is billed as 2 minutes. | Audio length | Tokens | USD | |---|---|---| | Up to 1 min | 0.1 | $0.002 | | 1 min 1 s – 2 min | 0.2 | $0.004 | | 20 min (maximum) | 2 | $0.04 | **Result**: two `json` items, vocals first: ```json [ { "type": "audio", "name": "vocals", "value": "https://...mp3" }, { "type": "audio", "name": "instrumental", "value": "https://...mp3" } ] ``` Both are 44.1 kHz with the same number of channels as the source (a mono file gives mono tracks), and `.wav` links when `output_format` is `wav`. Result links expire (see `link_expired_at`). ## OpenAPI ````yaml api-reference/audio-generations/openapi-vocal-remover.json POST /api/v1/audio/generations openapi: 3.1.0 info: title: GoEnhance API - Vocal Remover description: Split a song or video soundtrack into vocals and instrumental. version: 1.0.0 servers: - url: https://api.goenhance.ai security: [] paths: /api/v1/audio/generations: post: tags: - AudioGenerations summary: Vocal Remover description: >- Separate any audio into two tracks: the **vocals** and everything else (the **instrumental**: music, beats and sound effects). Works on songs, podcasts, voice-overs over background music, and videos with sound (the first audio track is used). - One request always returns both tracks. - The billed length is the length of `audio_url`, measured before the task is accepted. **Pricing**: 0.1 tokens ($0.002) per minute of audio, rounded up to the whole minute. A 61-second file is billed as 2 minutes. | Audio length | Tokens | USD | |---|---|---| | Up to 1 min | 0.1 | $0.002 | | 1 min 1 s – 2 min | 0.2 | $0.004 | | 20 min (maximum) | 2 | $0.04 | **Result**: two `json` items, vocals first: ```json [ { "type": "audio", "name": "vocals", "value": "https://...mp3" }, { "type": "audio", "name": "instrumental", "value": "https://...mp3" } ] ``` Both are 44.1 kHz with the same number of channels as the source (a mono file gives mono tracks), and `.wav` links when `output_format` is `wav`. Result links expire (see `link_expired_at`). parameters: - name: Authorization in: header description: '' required: false example: '{{Authorization}}' schema: type: string requestBody: content: application/json: schema: type: object properties: model: type: string enum: - vocal-remover description: Model name. Must be `vocal-remover`. audio_url: type: string format: uri description: >- The audio to separate. A public `https://` link to an audio file (mp3, m4a, wav, flac, ogg) or a video with sound (mp4, mov, webm; its first audio track is used), 1 second to 20 minutes, up to 200 MB. Its length is measured before the task is accepted and is the billed length. output_format: type: string enum: - mp3 - wav default: mp3 description: >- `mp3` (320 kbps, default) or `wav` (16-bit). Both tracks use the same format. custom_callback_url: type: string format: uri description: >- Optional. A publicly accessible HTTPS URL. When the task status changes (processing / success / failed), GoEnhance sends a POST request to this URL. The request body is identical to the response of GET /api/v1/jobs/detail. If your server does not respond with HTTP 200, the notification is retried up to 3 times, with a 3-second timeout per attempt. example: https://your-server.com/goenhance/callback required: - model - audio_url example: model: vocal-remover audio_url: https://example.com/song.mp3 responses: '200': description: '' content: application/json: schema: type: object properties: code: type: integer msg: type: string data: type: object properties: img_uuid: type: string cost: type: number description: >- Tokens deducted for this request. This is the amount actually charged, so it already reflects any discount active on your account and can be lower than the listed price. Tokens are deducted when the task is accepted, and refunded automatically if the generation ends in failure. example: 0.2 required: - img_uuid - cost required: - code - msg - data examples: '1': summary: Success value: code: 0 msg: Success data: img_uuid: c12b656c-747a-44fd-9c80-add79b0c52d5 cost: 0.2 '2': summary: Insufficient tokens value: code: 100 msg: tokens is not enough quota: summary: API key quota exceeded value: code: 101 msg: 'API key quota exceeded: 4990 of 5000 tokens used (monthly)' bad: summary: Invalid parameters value: code: -1 msg: audio_url is too long. Max 20 minutes, got 1385.2s headers: {} '401': description: '' content: application/json: schema: type: object properties: code: type: integer msg: type: string headers: {} deprecated: false ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.