Generate Music
Generate AI music from text prompts using Suno V5. Each generation returns 2 song variations with cover art. 15 credits per generation. Simple mode or custom mode with lyrics, style, and title control.
API-only. Music generation is available exclusively through the VicSee API. Studio UI coming soon.
Pricing
| Model | Credits | Description |
|---|---|---|
| Suno V5 | 15 | AI music from text (2 songs per generation) |
Credits are deducted upfront. Refunded automatically if generation fails. Each generation produces 2 song variations with cover art.
Endpoint
POST https://vicsee.com/api/v1/generateSee Authentication for API key setup.
Simple Mode
Describe the music you want. Suno generates lyrics, melody, and arrangement automatically.
Parameters
model · string · required
Must be "suno-v5-generate-music".
input.prompt · string · required
A description of the desired music. Maximum 500 characters. Suno will auto-generate lyrics and arrangement based on this.
Good prompts are descriptive:
- "An upbeat electronic track for a product launch video"
- "Melancholy acoustic guitar ballad about saying goodbye"
- "90s hip-hop beat with heavy bass and vinyl scratches"
input.instrumental · boolean · optional
Set to true for instrumental-only (no vocals/lyrics).
Default: false
Example Request
curl -X POST https://vicsee.com/api/v1/generate \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "suno-v5-generate-music",
"input": {
"prompt": "An upbeat electronic track for a product launch video"
}
}'Instrumental Example
curl -X POST https://vicsee.com/api/v1/generate \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "suno-v5-generate-music",
"input": {
"prompt": "Calm lo-fi beats for studying",
"instrumental": true
}
}'Custom Mode
Full control over lyrics, style, and title. Set custom_mode to true.
Parameters
input.custom_mode · boolean · required
Must be true to enable custom mode.
input.title · string · required
Song title. Maximum 80 characters.
input.style · string · required
Music style/genre specification. Maximum 1,000 characters.
Examples: "Jazz", "Electronic, Upbeat, Synth-pop", "Dark ambient with orchestral swells"
input.lyrics · string · required (unless instrumental)
The exact lyrics to sing. Maximum 5,000 characters. Not required when instrumental is true.
Use Suno's formatting tags for structure:
[Verse],[Chorus],[Bridge],[Outro]for song sections[Instrumental Break]for instrumental passages within a vocal track
input.instrumental · boolean · optional
Set to true for instrumental-only. When true, lyrics is not required.
Default: false
input.vocal_gender · string · optional
Preferred vocal gender. Only effective in custom mode. Note: this increases the probability but does not guarantee the vocal gender.
Values: "m" (male), "f" (female)
input.negative_tags · string · optional
Styles to exclude from the generation.
Example: "Heavy Metal, Screaming"
Example Request
curl -X POST https://vicsee.com/api/v1/generate \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "suno-v5-generate-music",
"input": {
"custom_mode": true,
"title": "Launch Day",
"style": "Electronic, Upbeat, Synth-pop",
"lyrics": "[Verse]\nThe future starts today\nEvery pixel comes alive\n\n[Chorus]\nLaunch day, launch day\nWe built this from the ground up",
"vocal_gender": "f",
"negative_tags": "Heavy Metal"
}
}'Response
Step 1: Submit (200)
The generate endpoint returns a pending task immediately:
{
"success": true,
"data": {
"id": "task_abc123",
"model": "suno-v5-generate-music",
"status": "pending",
"creditsUsed": 15,
"creditsRemaining": 485,
"createdAt": "2026-03-01T12:00:00.000Z"
}
}Step 2: Poll for Result
Poll GET /api/v1/tasks/{id} until status is completed (typically 30-120 seconds):
curl https://vicsee.com/api/v1/tasks/task_abc123 \
-H "Authorization: Bearer YOUR_API_KEY"Step 3: Completed (songs)
{
"success": true,
"data": {
"id": "task_abc123",
"model": "suno/generate-music",
"status": "completed",
"mediaType": "music",
"result": {
"songs": [
{
"audio_url": "https://cdn.example.com/song1.mp3",
"image_url": "https://cdn.example.com/cover1.jpeg",
"duration": 198.44,
"title": "Launch Day",
"tags": "electronic, upbeat, synth-pop",
"prompt": "[Verse] The future starts today..."
},
{
"audio_url": "https://cdn.example.com/song2.mp3",
"image_url": "https://cdn.example.com/cover2.jpeg",
"duration": 212.28,
"title": "Launch Day",
"tags": "electronic, upbeat, synth-pop",
"prompt": "[Verse] The future starts today..."
}
]
},
"createdAt": "2026-03-01T12:00:00.000Z"
}
}Each generation produces 2 song variations. Audio URLs are temporary (14 days).
Coming Soon
Additional music operations are planned for future release:
- Extend Music — Continue a generated song
- Upload & Cover — Upload audio and re-style it
- Add Vocals / Instrumental — Add or remove vocals from a track
- Create Music Video — Generate a music video from a song
Limits
| Constraint | Value |
|---|---|
| Songs per generation | 2 variations |
| Max prompt length (simple) | 500 characters |
| Max lyrics length (custom) | 5,000 characters |
| Max style length (custom) | 1,000 characters |
| Max title length | 80 characters |
| Audio format | MP3 |
| Audio URL expiry | 14 days |
Errors
| Code | HTTP | Description |
|---|---|---|
MISSING_PROMPT | 400 | prompt not provided (simple mode) |
PROMPT_TOO_LONG | 400 | Prompt exceeds 500 characters |
MISSING_STYLE | 400 | style not provided (custom mode) |
STYLE_TOO_LONG | 400 | Style exceeds 1,000 characters |
MISSING_TITLE | 400 | title not provided (custom mode) |
TITLE_TOO_LONG | 400 | Title exceeds 80 characters |
MISSING_LYRICS | 400 | lyrics not provided (custom mode, non-instrumental) |
LYRICS_TOO_LONG | 400 | Lyrics exceed 5,000 characters |
INVALID_VOCAL_GENDER | 400 | vocal_gender not "m" or "f" |
INSUFFICIENT_CREDITS | 402 | Not enough credits |
GENERATION_FAILED | 500 | Provider failed |
Related
- ElevenLabs Audio — Voiceover, TTS, and sound effects
- Merge Audio + Video — Combine generated music with video
- Credits API — Check your credit balance
ElevenLabs Audio
Generate multi-speaker voiceovers, single-speaker narration, and sound effects with ElevenLabs models through VicSee API. V3 Dialogue, TTS Turbo 2.5, and Sound Effect V2.
Character Creation
Train a consistent character identity from photos (FLUX LoRA). Upload 10-30 images, get a character ID, then generate unlimited consistent images via API. 500 credits per training, 15 credits per image.