You're using a guest profile, so some things are limited:
  • Your jobs are deleted 1 day after they finish
  • Up to 25 steps, 1 image per job, 1024×1024 max size, no LoRAs
  • 10 jobs an hour, 30 a day
  • No Flux, Qwen Image, Flux Kontext, Qwen Edit, Relight, Image to 3D
  • No save prompts, save images, share links, zip downloads, the API
Sign up free
Find voices voice-models.com

Added voices are shared: everyone on the site can use them. Only Hugging Face downloads work here.

Audio (WAV, MP3, FLAC, OGG, M4A…) or a video, up to 15 minutes — speech to text and subtitle resync take up to 3 hours, so a whole movie works (videos and files over 50 MB need an account, up to 4 GB; only the sound is kept). Results are FLAC files (lossless, about half the size of WAV). Clean-up returns 16 kHz mono speech. Speech to text returns a transcript and .srt subtitles. Change voice works best on clean vocals; tick "keep the music" for a song.

Audio Tools

Open History

Audio

About Audio Tools

Split a song into vocals, drums, bass and the rest, make a karaoke track, take background noise out of speech, transcribe audio or video to text and subtitles (with translation), change a voice, or fix a subtitle file's timings.

Is it free?

Yes. This is a free, non-commercial project. Many tools work without an account; a free account unlocks the rest and higher limits.

What happens to my images?

Nothing is shared unless you make a share link. Without an account your results are deleted a day after they finish; with an account they stay in your History until you delete them.

Can I use it from my own code?

Yes. With an account you can create an API key and use the REST API or the MCP endpoint.

Before you start

This site makes AI images, edits and audio, and some models can make adult content. To use it you must be 18 or older and agree to the Terms of Service (and our Privacy Policy). In short:

Leave