# AI karaoke maker and instrumental maker

Turn any song or music video into a clean instrumental backing track.

Powered by [Vocal remover](https://audo.ai/vocal-remover.md) — pre-set to export the instrumental backing track.

## How it works

1. Choose a song or music video from your device.
2. Press Make instrumental to remove the lead and backing vocals.
3. Play the backing track right away and download the instrumental (plus the isolated vocal).

## Studio-grade backing tracks for rehearsals, covers, and live shows

Audo's AI karaoke maker and instrumental maker — powered by [Vocal remover](https://audo.ai/vocal-remover.md) — turns any song or video into a clean backing track (WAV, MP3, M4A, AAC, FLAC, OGG, Opus, WebM, AIFF, MP4, MOV, MKV, WebM, AVI) up to 10 GB without an account, with the first 45 seconds free 3 times a day and no sign-up. Singers preparing for auditions, wedding bands learning requests, and choir directors making rehearsal tracks often need an instrumental version that was never released officially.

Standard karaoke tracks re-recorded by session bands rarely match the tempo rubato, key changes, or horn arrangements of the real record. By removing vocals directly from the original master with Mel-Band RoFormer and keeping the exact stereo residual, Audo gives you the authentic arrangement with the lead singer taken out.

After downloading your instrumental, you can trim a long intro or fade out an ending in [Cut audio](https://audo.ai/audio-cutter.md), or match the playback level across a whole setlist with [Boost volume](https://audo.ai/volume-booster.md).

Tool: Separate vocals (`separate_vocals`). The same tool's other pages: https://audo.ai/vocal-remover.md. Price: 8 credits a minute — $0.08/min ($4.80/hr), pay-as-you-go with no monthly subscription — of input for whole files, charged only when a job succeeds.

## Free API

```bash
curl -F file=@song.mp3 -F keep=instrumental https://audo.ai/api/try/separate-vocals -D response.headers -o response.body
```

Read response.headers and response.body before naming media. Handle 202, 200 JSON and errors with the complete response client at https://audo.ai/docs/api?utm_source=markdown&utm_medium=agent#responses.

Free for the first 45 seconds of each file, 3 times a day per person, with no key or account. Uploads up to 10 GB, 2 at once from one address. The response is the result itself; a job that runs longer than about 30 seconds returns 202 with a link to check on it. With an API key (`-H "Authorization: Bearer $AUDO_API_KEY"`), omitting free runs the full job with credits if the balance covers it, otherwise the free allowance if quota remains. Set free=true to prohibit spending; for paid runs use free=false with an approved positive max_credits. A free result cut short comes with finishUrl (and the Audo-Finish-Url header when the response is the file itself): give it to the person, who pays there (from $5, no sign-up), and the whole file runs; keep checking the status link, whose finishedBy names the whole-file job and its own status link. Details: https://audo.ai/docs/api.md

## Options

Form fields with the same names as the MCP tool's inputs:

- `keep`: Which track comes first. Both are returned.
- `output_format`: The result's format: same (as the input; a video stays a video), wav, mp3, m4a, or flac. Default same.

## Languages

Any language: it works on the sound, not the words.

## From an assistant (MCP)

Add https://audo.ai/mcp and sign in (setup for each assistant: https://audo.ai/setup.md). The tool is `separate_vocals`:

> Separates singing from a song into two stereo tracks: vocals and instrumental. Always returns both; keep selects the first output. Use split_audio for four music stems, separate_scene for spoken dialogue and scene sound, or separate_sound for a named sound. With output_format same, the first output keeps the original video picture. Costs 8 credits a minute, charged only on success; free for the first 45 seconds, 3 times a day. Returns download links, or job_id for get_job.

Example: "Use Audo to make a karaoke instrumental track from song.mp3."

## Questions

**Is it free?** Yes. Audo is free for the first 45 seconds of each file, 3 times a day, with no sign-up. Whole files are $0.08 a minute ($4.80 an hour), with no subscription — [see pricing](https://audo.ai/pricing.md).

**Does it keep the original video on a music video?** Yes. When you upload an MP4 or MOV music video to Audo with Output format set to Same as the original, the first download is the video itself with the instrumental backing track in place of the singing.

**Do guitars, pianos, and drums stay at full quality?** Yes. Because Audo creates the backing track by subtracting only the isolated vocal waveform from the original stereo mix, acoustic instruments, synth pads, and drum punch stay crisp.

**Can I generate timed lyrics or captions for the song too?** Yes. If you have the song's lyrics, run the original track through Audo's [Text to SRT](https://audo.ai/text-to-srt.md) to line up every line with the music, or use [Transcribe audio](https://audo.ai/transcribe.md) to generate timed captions.

**Can I record my own singing over the backing track?** Yes. Download the instrumental track from Audo, record your vocal take in [Voice recorder](https://audo.ai/voice-recorder.md), and blend both together with [Mix audio](https://audo.ai/mix-audio.md).

**Does it also give me the vocals on their own?** Yes. Alongside the primary instrumental file, Audo includes the isolated vocal track so you can check phrasing, harmonies, or cues whenever you need them.

## More

- Other music tools: [Vocal remover](https://audo.ai/vocal-remover.md), [Stem splitter](https://audo.ai/stem-splitter.md), [Change pitch](https://audo.ai/change-pitch.md), [Change speed](https://audo.ai/change-speed.md), [Key and BPM](https://audo.ai/key-bpm-finder.md), [AI music generator](https://audo.ai/ai-music-generator.md), [Reverse audio](https://audo.ai/reverse-audio.md)
- Related guides: [Best AI stem splitters](https://audo.ai/guides/best-ai-stem-splitters.md), [LALAL.AI Stem Splitter: free limit and alternatives](https://audo.ai/guides/lalal-ai-stem-splitter.md)
- [All tools](https://audo.ai/all-tools.md)
- [Prices and free limits](https://audo.ai/pricing.md)
- [Set up your assistant](https://audo.ai/setup.md)
- Every tool: https://audo.ai/llms.txt
- OpenAPI: https://audo.ai/api/openapi.json
- This page for people: https://audo.ai/karaoke-maker?utm_source=markdown&utm_medium=agent
