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
Google Lyria 3 Pro is Google’s premium AI music generation model. Describe the sound you want in natural language — genre, tempo, instruments, mood, and style — and get a higher-fidelity music clip with richer detail and more nuanced musical expression than the standard Clip tier. Optionally guide the output with a reference image or refine it with a negative prompt.
- Looking for a lower-cost option? Try Google Lyria 3 Clip
Why Choose This?
-
Premium music generation quality Richer instrumentation, more nuanced musical expression, and higher audio fidelity than the Clip tier.
-
Detailed text-to-music control Describe your track with genre, BPM, instruments, energy level, and mood for precise, on-target results.
-
Image-guided generation Upload a reference image to inspire the musical mood and atmosphere of the clip.
-
Negative prompt support Specify what you don’t want in the track — exclude instruments, styles, or characteristics for more precise control.
-
Reproducible results Use the seed parameter to lock in a specific output for exact reproduction across runs.
-
Prompt Enhancer Built-in tool to automatically refine your music descriptions for richer results.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the desired music style, genre, tempo, and instruments. |
| image | No | Reference image to guide the mood and atmosphere of the generated music. |
| negative_prompt | No | Elements to exclude from the generated track. |
| seed | No | Random seed for reproducible results. |
How to Use
- Write your prompt — describe the genre, tempo, instruments, mood, and style. Use the Prompt Enhancer for better results.
- Upload a reference image (optional) — provide an image to inspire the musical atmosphere.
- Add a negative prompt (optional) — specify sounds, styles, or elements you want to avoid.
- Set a seed (optional) — fix the seed to reproduce a specific result in future runs.
- Submit — generate and download your music clip.
Example Prompt
Dark ambient sci-fi underscore, deep pulsing bass drones, ethereal synth pads, subtle percussion, tense and mysterious, space horror atmosphere, no melody, slow tempo.
Pricing
Just $0.08 per clip.
Best Use Cases
- Film & Video Scoring — Generate high-quality music beds and underscore for professional video productions.
- Game & Interactive Media — Produce rich atmospheric tracks and dynamic soundscapes for games and apps.
- Advertising & Brand Content — Create polished custom music for campaigns without licensing fees.
- Podcast & Streaming — Generate premium intro, outro, and background music for audio content.
- Creative Production — Rapidly prototype and explore musical styles with professional-grade output.
Pro Tips
- Be specific about BPM, key instruments, and energy level for the most accurate results.
- Use negative_prompt to exclude unwanted elements like vocals, specific instruments, or genres.
- Fix the seed once you find a style you like to iterate on it consistently.
- Try pairing atmospheric images with a minimal prompt to let the image drive the mood.
- Use the Prompt Enhancer to expand a simple style reference into a detailed music description.
Notes
- Only prompt is required; all other parameters are optional.
- Please ensure your content complies with Google’s usage policies.
Related Models
- Google Lyria 3 Clip — Standard tier at $0.04 per clip for cost-efficient music generation.
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 |