suno_generate_custom_music
Generate custom AI music by providing your own lyrics with section markers, song title, and music style. Control every aspect of the song creation process.
Instructions
Generate AI music with full control over lyrics, title, and style (Custom Mode).
This gives you complete creative control over the song. You provide the lyrics
with section markers, and Suno generates the melody and arrangement.
Use this when:
- You have specific lyrics you want to use
- You want precise control over the music style
- You need a specific song title
- You want to specify vocal gender (v4.5+ models)
- You want the API to auto-generate lyrics from a prompt (use lyric_prompt)
For quick generation without writing lyrics, use suno_generate_music instead.
Returns:
Task ID and generated audio information including URLs, title, lyrics, and duration.Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| lyric | No | Song lyrics with section markers. Use [Verse], [Chorus], [Pre-Chorus], [Bridge], [Outro], [Intro] to structure the song. Example: [Verse 1] Walking down the empty street Rain is falling at my feet [Chorus] But I keep moving on Until the break of dawn. Leave empty when using lyric_prompt to auto-generate lyrics. | |
| title | No | Title of the song. Keep it concise and memorable. | |
| style | No | Music style description. Be specific about genre, mood, tempo, and instruments. Examples: 'upbeat pop rock, energetic drums, electric guitar', 'acoustic folk, gentle, fingerpicking', 'dark electronic, synthwave, 80s retro' | |
| model | No | Suno model version. 'chirp-v5-5' or 'chirp-v5' recommended for best quality. | chirp-v5-5 |
| instrumental | No | If true, generate instrumental version (lyrics will be ignored). Default is false. | |
| lyric_prompt | No | Prompt for auto-generating lyrics. Only used when custom is true and lyric is empty. Provide a dict with the lyric generation parameters (e.g. {'prompt': 'A song about winter'}). | |
| style_negative | No | Styles to explicitly exclude from the generation. Examples: 'heavy metal, screaming', 'autotune, electronic' | |
| vocal_gender | No | Preferred vocal gender. 'f' for female, 'm' for male, empty string for AI to decide. Only works with v4.5+ models. | |
| variation_category | No | Variation intensity for v5+ models. 'high' for maximum variation, 'normal' for balanced, 'subtle' for minimal changes. Only supported in chirp-v5 and above. | |
| weirdness | No | Advanced parameter for custom mode. Controls how unusual/experimental the generation is. | |
| style_influence | No | Advanced parameter for custom mode. Controls how strongly the style prompt influences the generation. | |
| callback_url | No | Webhook callback URL for asynchronous notifications. When provided, the API will call this URL when the audio is generated. |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |