Vidu Contest
WaveSpeed.ai
Beranda/Jelajahi/Generate Music/wavespeed-ai/heartmula/generate-music
text-to-audio

text-to-audio

HeartMuLa

wavespeed-ai/heartmula/generate-music

HeartMuLa is a state-of-the-art music generation model that creates high-quality songs from lyrics and style tags. Ready-to-use REST inference API with best performance, no coldstarts, and affordable pricing.

Input

Idle

Permintaan Anda akan membutuhkan $0.08 per run.

Untuk $1 Anda dapat menjalankan model ini sekitar 12 kali.

ContohLihat semua

README

HeartMuLa Generate Music

HeartMuLa is an open-source music foundation model that generates high-quality songs from lyrics and style tags. It supports multilingual lyrics including English, Chinese, Japanese, Korean, and Spanish — delivering complete songs with vocals and instrumentals.

Why Choose This?

  • Complete song generation Creates full songs with vocals and instrumentals from lyrics and style tags.

  • Multilingual lyrics Supports English, Chinese, Japanese, Korean, and Spanish.

  • Structured song composition Use section markers ([Verse], [Chorus], [Bridge], etc.) for precise song arrangement.

  • Flexible style control Use comma-separated tags to define genre, mood, instruments, tempo, and vocal characteristics.

  • Instrumental sections Include intros, outros, and instrumental breaks with duration control.

Parameters

ParameterRequiredDescription
lyricsYesSong lyrics with structure markers
tagsNoStyle tags: genre, mood, instruments, tempo, etc.
seedNoRandom seed for reproducibility

Tags Format

Tags describe the overall musical style using comma-separated values. You can specify:

  • Gender: male, female
  • Timbre: dark, bright, soft
  • Genre: pop, jazz, rock, R&B, folk, metal, reggae, etc.
  • Emotion: sad, happy, energetic, romantic, soulful
  • Instruments: piano, drums, guitar, synthesizer
  • Tempo: e.g., "85bpm"

Examples:

r&b, smooth, male vocals, soulful, slow jam, romantic, 85bpm

piano, happy, wedding, synthesizer, romantic

female, dark, pop, sad, piano and drums, 125bpm

Lyrics Format

Use structure markers in brackets to guide song arrangement:

Vocal sections (require lyrics):

  • [Verse] — Verse section
  • [Chorus] — Chorus/hook section
  • [Bridge] — Bridge section

Instrumental sections (no lyrics needed):

  • [intro-short] — Short intro (approx. 0-10 seconds)
  • [intro-medium] — Medium intro (approx. 10-20 seconds)
  • [inst-short] — Short instrumental break (approx. 0-10 seconds)
  • [inst-medium] — Medium instrumental break (approx. 10-20 seconds)
  • [outro-short] — Short outro (approx. 0-10 seconds)
  • [outro-medium] — Medium outro (approx. 10-20 seconds)

Example:

[intro-short] [Verse] Your voice like velvet, I'm never alone The way you say my name, it pulls me in A love like ours is more than skin [Chorus] Stay with me until the morning light Hold me close and never let me go [outro-short]

How to Use

  1. Enter your lyrics — provide structured lyrics with section markers.
  2. Add tags (optional) — describe the musical style with comma-separated tags.
  3. Set seed (optional) — use a specific seed for reproducible results.
  4. Run — submit and download your generated song.

Pricing

OutputCost
Per song$0.08

Best Use Cases

  • Original Music Creation — Generate complete songs for creative projects.
  • Demo Production — Quickly prototype song ideas before full production.
  • Multilingual Content — Create songs in English, Chinese, Japanese, Korean, or Spanish.
  • Content Soundtracks — Create custom music for videos, podcasts, and games.
  • Songwriting Assistance — Hear your lyrics set to music instantly.

Pro Tips

  • Combine multiple style tags for specific results (e.g., "female, bright, pop, happy, piano, 130bpm").
  • Use [intro-short] and [outro-short] for quick intros/outros, or medium versions for longer sections.
  • Add [inst-short] or [inst-medium] between vocal sections for instrumental breaks.
  • Keep lyrics well-structured with clear section markers for better song arrangement.
  • Use the same seed to reproduce identical results.

Notes

  • Lyrics is the only required field.
  • Supported lyrics languages: English, Chinese, Japanese, Korean, Spanish.
  • Song length depends on lyrics length and structure markers.
  • Instrumental sections (intro, inst, outro) do not require lyrics text.