> ## 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. # Suno Add Instrumental > Add a full backing track to a vocal-only recording (a cappella, humming, singing). Each request returns **2 versions**. **Pricing** (per request): | Option | Tokens | USD | |---|---|---| | Per request (2 versions) | 3.9 | $0.078 | Returns an `img_uuid`; poll GET /api/v1/jobs/detail (or use `custom_callback_url`) for the result. On success, `json` holds **one item per song** (normally 2): ```json { "type": "audio", "value": "https://cdn4.goenhance.ai/source2/.../output.mp3", "audio_id": "e231a3f0-...", "title": "Rainy Night", "audio_duration": 187.4, "style": "lofi hip hop, mellow piano", "lyrics": "[Verse] ..." } ``` Keep the task's `img_uuid` and each song's `audio_id`: that pair is how you extend the song, export WAV, make a music video, split stems or get timestamped lyrics later. Result links expire (see `link_expired_at`), so download the files you want to keep. ## OpenAPI ````yaml api-reference/audio-generations/openapi-suno-add-instrumental.json POST /api/v1/audio/generations openapi: 3.1.0 info: title: GoEnhance API - Suno Add Instrumental description: Add a full backing track to a vocal-only recording. version: 1.0.0 servers: - url: https://api.goenhance.ai security: [] paths: /api/v1/audio/generations: post: tags: - AudioGenerations summary: Suno Add Instrumental description: >- Add a full backing track to a vocal-only recording (a cappella, humming, singing). Each request returns **2 versions**. **Pricing** (per request): | Option | Tokens | USD | |---|---|---| | Per request (2 versions) | 3.9 | $0.078 | Returns an `img_uuid`; poll GET /api/v1/jobs/detail (or use `custom_callback_url`) for the result. On success, `json` holds **one item per song** (normally 2): ```json { "type": "audio", "value": "https://cdn4.goenhance.ai/source2/.../output.mp3", "audio_id": "e231a3f0-...", "title": "Rainy Night", "audio_duration": 187.4, "style": "lofi hip hop, mellow piano", "lyrics": "[Verse] ..." } ``` Keep the task's `img_uuid` and each song's `audio_id`: that pair is how you extend the song, export WAV, make a music video, split stems or get timestamped lyrics later. Result links expire (see `link_expired_at`), so download the files you want to keep. 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: - suno-add-instrumental description: Model name. Must be `suno-add-instrumental`. audio_url: type: string format: uri description: Required. Public URL of the vocal-only recording. title: type: string maxLength: 80 description: Required. Song title. Max 80 characters. style: type: string maxLength: 1000 description: >- Required. Style of the backing track, e.g. `lofi, jazzy chords, soft drums`. Max 1000 characters. lyrics: type: string maxLength: 5000 description: >- Optional. The lyrics sung in the recording, to help align the arrangement. Use section markers such as `[Verse]` and `[Chorus]`. Max 5000 characters. variant: type: string enum: - standard - mini - wild default: standard description: >- Suno V6 flavor. `standard` = V6 (natural vocals, rich detail), `mini` = V6 Mini (lighter and faster), `wild` = V6 Wild (bolder, more experimental). All three cost the same. negative_tags: type: string maxLength: 200 description: >- Optional. Styles or traits to avoid, e.g. `heavy metal, screaming`. Max 200 characters. vocal_gender: type: string enum: - male - female description: >- Optional. Preferred singer gender (`m` / `f` also accepted). This raises the probability; it is not guaranteed. style_weight: type: number minimum: 0 maximum: 1 description: >- Optional. How strictly to follow `style`, from 0 to 1 (rounded to 2 decimals). weirdness_constraint: type: number minimum: 0 maximum: 1 description: >- Optional. How experimental the result may be, from 0 to 1 (rounded to 2 decimals). audio_weight: type: number minimum: 0 maximum: 1 description: >- Optional. How much the result follows the audio features of the source, from 0 to 1 (rounded to 2 decimals). Not available when `instrumental` is `true`. variety: type: integer minimum: 0 maximum: 4 default: 1 description: >- Optional. How different the versions are from each other: 0 off, 1 normal (default), 2 high, 3 extra, 4 max. 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 - title - style example: model: suno-add-instrumental audio_url: https://example.com/acapella.mp3 title: Morning Song style: acoustic pop, piano, light percussion 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: 3.9 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: 3.9 '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: >- lyrics is required when custom_mode is true and instrumental is false headers: {} '401': description: '' content: application/json: schema: type: object properties: code: type: integer msg: type: string headers: {} deprecated: false ````