> ## 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. # Cadence Voice Cover > Convert the vocals of a song to the voice in a short reference clip. The melody, lyrics and accompaniment stay the same: the lead vocal is separated, converted to the reference voice, and mixed back with the original accompaniment. - `reference_audio_url`: at least 3 seconds of one clear voice; 5 to 25 seconds of dry vocal (no music, little reverb) works best. Longer clips are cut to about 25 seconds at a pause. - `pitch_shift` moves only the vocal by whole semitones: use `-12` when a song sung by a female voice is converted to a male voice, `12` for the reverse. Shifts other than whole octaves may clash with the accompaniment. - The result is as long as the original song, which is also the billed length. - Only use voices you own or have permission to use. **Pricing**: 0.02 tokens ($0.0004) per second of audio, rounded up to the whole second. | Option | Tokens | USD | |---|---|---| | Per second of audio | 0.02 | $0.0004 | **Result**: one `json` item `{ "type": "audio", "value": "https://...mp3" }` (a `.wav` link when `output_format` is `wav`), 48 kHz stereo. Result links expire (see `link_expired_at`). ## OpenAPI ````yaml api-reference/audio-generations/openapi-cadence-voice-cover.json POST /api/v1/audio/generations openapi: 3.1.0 info: title: GoEnhance API - Cadence Voice Cover description: Make a song sound like it is sung by another voice. version: 1.0.0 servers: - url: https://api.goenhance.ai security: [] paths: /api/v1/audio/generations: post: tags: - AudioGenerations summary: Cadence Voice Cover description: >- Convert the vocals of a song to the voice in a short reference clip. The melody, lyrics and accompaniment stay the same: the lead vocal is separated, converted to the reference voice, and mixed back with the original accompaniment. - `reference_audio_url`: at least 3 seconds of one clear voice; 5 to 25 seconds of dry vocal (no music, little reverb) works best. Longer clips are cut to about 25 seconds at a pause. - `pitch_shift` moves only the vocal by whole semitones: use `-12` when a song sung by a female voice is converted to a male voice, `12` for the reverse. Shifts other than whole octaves may clash with the accompaniment. - The result is as long as the original song, which is also the billed length. - Only use voices you own or have permission to use. **Pricing**: 0.02 tokens ($0.0004) per second of audio, rounded up to the whole second. | Option | Tokens | USD | |---|---|---| | Per second of audio | 0.02 | $0.0004 | **Result**: one `json` item `{ "type": "audio", "value": "https://...mp3" }` (a `.wav` link when `output_format` is `wav`), 48 kHz stereo. 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: - cadence-voice-cover description: Model name. Must be `cadence-voice-cover`. audio_url: type: string format: uri description: >- The original song. A public `https://` link to an audio file (mp3, m4a, wav, flac, ogg; a video link uses its audio track), 5 to 360 seconds, up to 20 MB. mp3 or m4a is recommended: a full 6-minute song fits, while wav over about 1 minute 50 seconds or flac over about 3.5 minutes exceeds the limit. Its length is measured before the task is accepted and is the billed length. reference_audio_url: type: string format: uri description: >- The target voice. A public `https://` link to an audio file, at least 3 seconds of one clear voice, up to 20 MB. pitch_shift: type: integer minimum: -12 maximum: 12 default: 0 description: >- Optional. Shift the converted vocal by this many semitones, -12 to 12. Accompaniment is not shifted. output_format: type: string enum: - mp3 - wav default: mp3 description: '`mp3` (320 kbps, default) or `wav` (16-bit). 48 kHz stereo.' 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 - reference_audio_url example: model: cadence-voice-cover audio_url: https://example.com/original-song.mp3 reference_audio_url: https://example.com/my-voice.wav pitch_shift: -12 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: 0.86 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: 0.86 '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: >- reference_audio_url is too short. It needs at least 3 seconds of clear voice 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.