Mureka Ai Mureka V7.6 Generate Bgm
Playground
Try it on WavespeedAI!Mureka AI V7.6 Generate BGM is a fast AI music generation model that creates high-quality background music via the official Mureka API. Ready-to-use REST inference API for AI BGM generation, video soundtracks, game music, podcast intros, advertising audio, social media content, and professional music production workflows with simple integration, no coldstarts, and affordable pricing.
Features
Mureka AI V7.6 Generate BGM
Mureka AI V7.6 Generate BGM creates background music tracks from a text prompt, with optional instrumental reference guidance and support for multiple generations in a single request. It is suitable for videos, podcasts, ads, games, livestreams, and other content workflows that need original non-vocal music.
Why Choose This?
-
Prompt-based background music generation Generate instrumental tracks from a natural-language description of mood, genre, tempo, or instrumentation.
-
Optional instrumental reference guidance Use
instrumental_idto guide the generation toward a particular musical direction. -
Multiple generations per run Generate up to
3background music tracks in one request withnumber_of_songs. -
Flexible output formats Export generated tracks as
mp3,wav, orflac. -
Simple pricing Pricing depends only on how many tracks you generate.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Prompt describing the background music. Official limit: up to 1024 characters. |
| number_of_songs | No | Number of generations. Range: 1–3. Default: 1. |
| output_format | No | Output audio format after re-uploading to WaveSpeed CDN. Supported values: mp3, wav, flac. Default: mp3. |
| instrumental_id | No | Optional Mureka uploaded instrumental reference file ID. |
How to Use
- Write your prompt — describe the mood, genre, tempo, instrumentation, and production style you want.
- Add an instrumental reference (optional) — provide
instrumental_idif you want stronger musical guidance. - Set number of songs — choose how many generations you want, from
1to3. - Choose output format — select
mp3,wav, orflac. - Submit — run the model and download the generated background music tracks.
Example Prompt
Dreamy female vocal pop song with soft electronic beat, emotional piano chords, atmospheric pads, catchy hook, romantic cinematic mood, modern pop production, clean mix, suitable for short video background music
Pricing
Pricing is based on number_of_songs.
| Number of Songs | Cost |
|---|---|
| 1 | $0.03 |
| 2 | $0.06 |
| 3 | $0.09 |
Billing Rules
- Each generated background music track costs $0.03
- Total price = $0.03 ×
number_of_songs output_formatandinstrumental_iddo not affect pricing
Best Use Cases
- Video background music — Generate instrumental tracks for vlogs, ads, explainers, and short-form content.
- Podcast and livestream music — Create intro, outro, or ambient background tracks.
- Game and app audio — Produce mood-based background music for interactive experiences.
- Creative ideation — Explore multiple music directions from a single prompt.
- Reference-guided generation — Use an instrumental reference to steer the musical style more precisely.
Pro Tips
- Be specific in your prompt about genre, tempo, instrumentation, and mood.
- Use
number_of_songswhen you want multiple variations from the same idea. - Add
instrumental_idonly when you need tighter musical guidance. - Start with
mp3for convenience, then usewavorflacwhen higher-quality output matters more. - Short, focused prompts often produce more controllable results than overly broad descriptions.
Notes
promptis required.number_of_songssupports values from1to3.promptsupports up to1024characters.output_formatdefaults tomp3.- Pricing depends only on
number_of_songs.
Related Models
- Mureka AI V7.6 Generate Song — Create full songs from lyrics with optional style and reference guidance.
- Mureka AI V8 Generate BGM — Newer background music generation workflow with the same prompt-first interface.
- Mureka AI V9 Generate BGM — Latest background music generation workflow in the Mureka lineup.
- Mureka AI Stem Song — Process songs into stem-based outputs for remixing, editing, and production workflows.
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/mureka-ai/mureka-v7.6/generate-bgm" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
"number_of_songs": 1,
"output_format": "mp3"
}'
# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"
Parameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| prompt | string | Yes | - | Optional prompt describing the background music. Official limit: up to 1024 characters. | |
| number_of_songs | integer | No | 1 | 1 ~ 3 | Number of generations. Mureka charges per generated item. |
| output_format | string | No | mp3 | mp3, wav, flac | Output audio format after re-uploading to WaveSpeed CDN. |
| instrumental_id | string | No | - | - | Optional Mureka uploaded instrumental reference file ID. |
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.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. |
| 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 |