Browse ModelsWavespeed AIHeartmula Generate Music

Heartmula Generate Music

Heartmula Generate Music

Playground

Try it on WavespeedAI!

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.

Features

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$0.05

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.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result


# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/heartmula/generate-music" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "tags": "",
    "seed": -1
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"

Parameters

Task Submission Parameters

Request Parameters

ParameterTypeRequiredDefaultRangeDescription
lyricsstringYes--Song lyrics with structure tags. Each paragraph represents a segment starting with a structure tag (e.g., [verse], [chorus], [bridge]) and ending with a blank line. Each line is a sentence without punctuation.
tagsstringNo--Musical style tags (Optional). Describe the genre, mood, instruments, tempo, etc. For example: 'pop, upbeat, electronic, female vocals'.
seedintegerNo-1-1 ~ 2147483647The random seed to use for the generation. -1 means a random seed will be used.

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayArray of URLs to the generated content (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.has_nsfw_contentsarrayArray of boolean values indicating NSFW detection for each output
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Request Parameters

ParameterTypeRequiredDefaultDescription
idstringYes-Task ID

Result Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
dataobjectThe prediction data object containing all details
data.idstringUnique identifier for the prediction, the ID of the prediction to get
data.modelstringModel ID used for the prediction
data.outputsstringArray of URLs to the generated content (empty when status is not completed).
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
© 2025 WaveSpeedAI. All rights reserved.