Mureka Ai Mureka V8 Extend Song
Playground
Try it on WavespeedAI!Mureka AI V8 Extend Song is a fast AI music generation model that extends existing songs via the official Mureka API. Ready-to-use REST inference API for lengthening tracks, continuing song ideas, expanding demos, remix workflows, creative audio projects, and professional music production with simple integration, no coldstarts, and affordable pricing.
Features
Mureka AI V8 Extend Song
Mureka AI V8 Extend Song extends an existing song or audio track by generating a new continuation segment from the head or tail, guided by provided lyrics. It is suitable for song continuation, outro generation, intro extension, and other music editing workflows where you want to grow an existing track instead of generating a new one from scratch.
Why Choose This?
-
Song continuation workflow Extend an existing audio track with newly generated music and vocals.
-
Head or tail extension Choose whether to extend from the beginning or the end of the source audio.
-
Lyrics-guided extension Provide lyrics for the new segment so the continuation matches your intended content.
-
Simple extension control Use
extend_atto define where the extension should begin. -
Flexible output formats Export the extended result as
mp3,wav, orflac. -
Production-ready API Suitable for music editing, song completion, structure expansion, and content production workflows.
Parameters
| Parameter | Required | Description |
|---|---|---|
| audio | Yes | Source audio URL to extend. It will be uploaded to Mureka as audio. |
| lyrics | Yes | Lyrics for the extension segment. |
| extend_at | Yes | Extension position in milliseconds. |
| extend_type | No | Whether to extend from the tail or head of the source audio. Default: tail. |
| output_format | No | Output audio format after re-uploading to WaveSpeed CDN. Supported values: mp3, wav, flac. Default: mp3. |
How to Use
- Upload your source audio — provide the existing song or audio track you want to extend.
- Write the extension lyrics — enter the lyrics for the new segment.
- Set
extend_at— define the position in the source audio where the extension should begin. - Choose extension type — use
tailto extend from the end orheadto extend from the beginning. - Choose output format — select
mp3,wav, orflac. - Submit — run the model and download the extended song.
Example Use Case
Extend a demo track from the last chorus by adding a new lyrical outro section with matching musical style and vocal continuation.
Best Use Cases
- Song continuation — Add a new ending or next section to an existing track.
- Intro or outro generation — Extend the front or back of a song with new material.
- Demo finishing — Turn partial song ideas into more complete structures.
- Music editing workflows — Expand tracks without rebuilding them from scratch.
- Creative experimentation — Try alternate continuations from a chosen point in the song.
Pro Tips
- Use lyrics that match the tone and structure of the existing audio for smoother continuation.
- Choose
tailwhen you want to add a new ending or next section. - Choose
headwhen you want to generate an intro or earlier lead-in material. - Use
wavorflacwhen you want higher-quality outputs for further production work. - Make sure the source audio is clear and complete enough around the extension point for better results.
Notes
audio,lyrics, andextend_atare required.extend_atspecifies the position in the source audio where the extension begins.extend_atis measured in milliseconds.extend_typedefaults totail.output_formatdefaults tomp3.
Related Models
- Mureka AI V8 Generate Song — Create full songs from lyrics with optional style and reference guidance.
- Mureka AI V8 Generate BGM — Generate background music tracks from prompts.
- 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-v8/extend-song" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
"extend_at": 30000,
"extend_type": "tail",
"output_format": "mp3"
}'
# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"
Parameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| audio | string | Yes | - | - | Source audio URL to extend. It will be uploaded to Mureka as audio. |
| lyrics | string | Yes | - | - | Lyrics for the extension segment. |
| extend_at | integer | Yes | 30000 | - | Extension position in milliseconds. |
| extend_type | string | No | tail | tail, head | Extend from the tail or head of the source audio. |
| output_format | string | No | mp3 | mp3, wav, flac | Output audio format after re-uploading to WaveSpeed CDN. |
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 |