Google Lyria 3 Pro Music
Playground
Try it on WavespeedAI!Google Lyria 3 Pro generates high-quality music tracks from text prompts and optional image input. Pro tier delivers enhanced audio quality and richer compositions. Produces complete songs with lyrics, descriptions, and audio output. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Features
Google Lyria 3 Pro Music Generation
Google Lyria 3 Pro is Google’s premium AI music generation model that creates high-quality music tracks from text prompts. It can also accept optional image input to guide the musical style and mood. Pro tier delivers enhanced audio quality and richer compositions compared to the Clip variant. The model produces complete outputs including generated audio, lyrics, and a text description of the music.
Model Highlights
- Premium text-to-music generation with enhanced audio quality
- Optional image input for visual-guided music creation
- Generates lyrics and music description alongside audio
- Richer compositions compared to Clip tier
- 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
- Professional background music for video production
- High-quality original soundtrack creation
- Image-inspired music composition for creative projects
- Commercial music production and prototyping
- Premium audio content for apps and games
- Advertising and brand audio creation
Pricing
- $0.08 per generation
How to Use
- Write a prompt describing the desired music (genre, mood, instruments, tempo)
- Optionally provide an image to guide the musical atmosphere
- Optionally add a negative_prompt to exclude unwanted elements
- Optionally set a seed for reproducible results
- Submit via REST API endpoint
- Receive generated audio, lyrics, and description
API Integration
Simple REST API call with text prompt as the primary input. The model generates complete high-quality 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
- Pro tier offers higher audio quality than Clip at a higher price point
- 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-pro/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
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| prompt | string | Yes | - | The positive prompt for the generation. | |
| image | string | No | - | The image for generating the output. | |
| negative_prompt | string | No | - | A description of what to exclude from the generated audio. | |
| seed | integer | No | - | -1 ~ 2147483647 | The random seed to use for the generation. -1 means a random seed will be used. |
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Array of URLs to the generated content (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.has_nsfw_contents | array | Array of boolean values indicating NSFW detection for each output |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |
Result Request Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| id | string | Yes | - | Task ID |
Result Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction, the ID of the prediction to get |
| data.model | string | Model ID used for the prediction |
| data.outputs | string | Array of URLs to the generated content (empty when status is not completed). |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |