Suno

Generate music, lyrics, and audio with the Suno model

Suno Model

Unofficial API — sunor is not affiliated with, endorsed by, or officially connected to Suno Inc. This is a third-party integration that provides programmatic access to Suno’s music generation capabilities.

Suno is an AI music generation model that can create songs with vocals, instrumental tracks, and lyrics from text descriptions.

Available task types

Task Type	Credits	Description
music	10	Generate a complete music clip with audio and optional vocals
lyrics	5	Generate song lyrics from a text prompt
upload	1	Upload an audio file for use as input to other tasks
concat	5	Concatenate clips into a longer composition

Model versions

Version	Description
chirp-v3-5	Previous generation model. Faster but lower quality
chirp-v4	Latest model (default). Higher quality output, better vocals and instrumentation

Set the model version using the mv field in the input object. If omitted, chirp-v4 is used by default.

---

Music generation modes

Inspiration mode

The simplest way to generate music. Provide a natural language description and let the AI handle everything — lyrics, melody, arrangement, and production.

When to use: You have a general idea but want the AI to make creative decisions.

{
  "model": "suno",
  "task_type": "music",
  "input": {
    "gpt_description_prompt": "An upbeat electronic dance track with a catchy synth melody",
    "make_instrumental": false,
    "mv": "chirp-v4"
  }
}

Key fields:

• gpt_description_prompt — Describe the music you want in plain language
• make_instrumental — Set to true if you want no vocals

Custom mode

Full control over lyrics and style. You provide the exact lyrics and specify genre/style tags.

When to use: You have specific lyrics or want precise genre control.

{
  "model": "suno",
  "task_type": "music",
  "input": {
    "prompt": "[Verse]\nStars are falling from the sky\nDancing shadows passing by\n\n[Chorus]\nWe are the dreamers of the night\nChasing every fading light",
    "tags": "indie rock, dreamy, reverb, female vocals",
    "negative_tags": "heavy metal, rap",
    "title": "Dreamers of the Night",
    "mv": "chirp-v4"
  }
}

Key fields:

• prompt — Your lyrics. Use structure tags like [Verse], [Chorus], [Bridge], [Outro]
• tags — Comma-separated style descriptors
• negative_tags — Styles to explicitly avoid
• title — Song title

Continuation mode

Extend an existing clip from a specific point. Use this to build longer songs by continuing from where a previous generation ended.

When to use: You want to extend a clip you already generated.

{
  "model": "suno",
  "task_type": "music",
  "input": {
    "continue_clip_id": "abc123-clip-id",
    "continue_at": 30,
    "prompt": "[Bridge]\nBut tonight we let it go",
    "mv": "chirp-v4"
  }
}

Key fields:

• continue_clip_id — The clip ID from a previous music task output
• continue_at — Timestamp in seconds to start the continuation
• prompt — Optional lyrics for the continuation

---

Lyrics generation

Generate song lyrics from a text description.

{
  "model": "suno",
  "task_type": "lyrics",
  "input": {
    "prompt": "A melancholy ballad about leaving home for the first time"
  }
}

---

Audio upload

Upload an audio file by providing a publicly accessible URL. The uploaded audio can then be used as input for other tasks.

{
  "model": "suno",
  "task_type": "upload",
  "input": {
    "url": "https://example.com/my-audio.mp3"
  }
}

---

Clip concatenation

Combine clips into a single longer track. Useful for assembling a full song from individually generated sections.

{
  "model": "suno",
  "task_type": "concat",
  "input": {
    "clip_id": "abc123-clip-id"
  }
}

---

Tips for better results

Be specific with descriptions

Instead of “a good song”, try “an upbeat indie pop song with jangly guitars, handclaps, and a catchy whistle hook in the chorus”.

Use structure tags

In custom mode, use [Verse], [Chorus], [Bridge], [Outro], and [Intro] to control song structure.

Leverage negative tags

Use negative_tags to steer away from unwanted styles rather than only specifying what you want.

Use chirp-v4 for quality

The chirp-v4 model produces noticeably better audio quality and more natural vocals than chirp-v3-5.