Browse ModelsGoogleGoogle Lyria 3 Clip Music

Google Lyria 3 Clip Music

Google Lyria 3 Clip Music

Playground

Try it on WavespeedAI!

Google Lyria 3 Clip generates novel music tracks from text prompts and optional image input. Produces complete songs with lyrics, descriptions, and audio output. Supports negative prompts and seed control for reproducible results. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Google Lyria 3 Clip Music Generation

Google Lyria 3 Clip is an AI music generation model that creates novel music tracks from text prompts. It can also accept optional image input to guide the musical style and mood. The model produces complete outputs including generated audio, lyrics, and a text description of the music.

Model Highlights

  • Text-to-music generation from natural language prompts
  • Optional image input for visual-guided music creation
  • Generates lyrics and music description alongside audio
  • Negative prompt support to exclude unwanted elements
  • Seed control for reproducible generation
  • REST API with consistent performance and no cold starts

Parameters

  • prompt (required): Text description of the desired music, including genre, mood, instruments, tempo, etc.
  • image (optional): Reference image to guide the musical style and atmosphere.
  • negative_prompt (optional): Description of elements to exclude from the generated audio.
  • seed (optional): Random seed for reproducible results. -1 for random.

Use Cases

  • Background music generation for videos and content
  • Original soundtrack creation from text descriptions
  • Image-inspired music composition
  • Rapid music prototyping and ideation
  • Social media content audio production
  • Game and app background music

Pricing

  • $0.04 per generation

How to Use

  1. Write a prompt describing the desired music (genre, mood, instruments, tempo)
  2. Optionally provide an image to guide the musical atmosphere
  3. Optionally add a negative_prompt to exclude unwanted elements
  4. Optionally set a seed for reproducible results
  5. Submit via REST API endpoint
  6. Receive generated audio, lyrics, and description

API Integration

Simple REST API call with text prompt as the primary input. The model generates complete music tracks with accompanying lyrics and descriptions.

Notes

  • Prompt is the only required parameter
  • Image input is optional and used for style/mood guidance
  • Output includes audio, lyrics text, and music description
  • Use negative prompts to steer away from unwanted musical elements

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/google/lyria-3-clip/music" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{}'

# 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
promptstringYes-The positive prompt for the generation.
imagestringNo-The image for generating the output.
negative_promptstringNo-A description of what to exclude from the generated audio.
seedintegerNo--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.