---
title: Song Inpaint — Voice Cloning | ModelsLab
description: Generate seamless song edits with voice cloning inpainting. Upload audio, specify segments, and regenerate vocals via API. Try Song Inpaint now.
url: https://modelslab.com/song-inpaint
canonical: https://modelslab.com/song-inpaint
type: website
component: Seo/ModelPage
generated_at: 2026-04-26T18:39:06.069013Z
---

Available now on ModelsLab · Voice & Audio

Song Inpaint
Inpaint Songs Seamlessly
---

[Try Song Inpaint](/models/sonauto/song-inpaint) [API Documentation](https://docs.modelslab.com)

Sample output

Edit Songs Precisely
---

Targeted Regeneration

### Replace Song Sections

Specify start and end times to regenerate only selected audio segments.

Voice Cloning Integration

### Clone Vocals Exactly

Use song inpaint voice cloning to match original singer timbre in edits.

API Simplicity

### Streamline Workflow

Access song inpaint API endpoint for fast, programmatic music modifications.

Examples

See what Song Inpaint can create
---

Copy any prompt below and try it yourself in the [playground](/models/sonauto/song-inpaint).

Pop Chorus Edit

“Upbeat pop chorus with layered harmonies, female vocals, 120 BPM, energetic vibe, precise voice cloning match”

Acoustic Verse Fill

“Soft acoustic guitar verse, male singer with warm tone, fingerpicking rhythm, natural breath sounds”

Techno Drop Inpaint

“Intense techno drop with synthesized vocals, heavy bassline, 140 BPM, club atmosphere”

Jazz Bridge Replace

“Smooth jazz bridge, scat singing female voice, upright bass and piano, improvisational feel”

For Developers

A few lines of code.
Inpaint vocals. One call.
---

ModelsLab handles the infrastructure: fast inference, auto-scaling, and a developer-friendly API. No GPU management needed.

- **Serverless:** scales to zero, scales to millions
- **Pay per second,** no minimums
- **Python and JavaScript SDKs,** plus REST API

[API Documentation ](https://docs.modelslab.com)

PythonJavaScriptcURL

Copy

```
<code>import requests

response = requests.post(
    "https://modelslab.com/api/v7/voice/song-inpaint",
    json={
  "key": "YOUR_API_KEY",
  "lyrics": "New lyrics for the sections",
  "init_audio": "https://cdn.sonauto.ai/generations2/audio_a598194b-d464-474c-b1e6-1c99f8f8e457_0.ogg"
}
)
print(response.json())</code>
```

FAQ

Common questions about Song Inpaint
---

[Read the docs ](https://docs.modelslab.com)

### What is song inpaint?

Song inpaint regenerates specific time segments of a song while preserving the rest. It supports voice cloning for vocal sections. Upload audio and define replace ranges.

### How does song inpaint voice cloning work?

It clones the original voice timbre into inpainted sections using reference audio. Specify prompts for style and lyrics. Output blends seamlessly with unchanged parts.

### What is the song inpaint API endpoint?

POST to Song Inpaint endpoint with audio file, timestamps, and prompt. Include optional lyrics and voice parameters. Returns edited audio file.

### Is there a song inpaint alternative?

Song Inpaint provides a direct API for music editing with voice cloning. It differs from image inpaint by focusing on audio continuity. Integrates easily in code.

### What audio formats does song inpaint model support?

Supports common formats like MP3 and WAV. Audio length up to 190 seconds. Mask start/end in seconds for precise control.

### How to use song inpaint model for extensions?

Store generated songs for inpainting, then reference sections to extend intros or outros. Combine parts from multiple tracks. Use composition plans for complex edits.

Ready to create?
---

Start generating with Song Inpaint on ModelsLab.

[Try Song Inpaint](/models/sonauto/song-inpaint) [API Documentation](https://docs.modelslab.com)

---

*This markdown version is optimized for AI agents and LLMs.*

**Links:**
- [Website](https://modelslab.com)
- [API Documentation](https://docs.modelslab.com)
- [Blog](https://modelslab.com/blog)

---
*Generated by ModelsLab - 2026-04-27*