OpenModels
AI audio studio — voice cloning, dubbing, speech and lipsync
Clone a voice from a short sample, dub a video into another language, generate speech and sound effects, and lipsync any face to any track — in one studio, with the same account and credits as the image and video tools.
Which plan: The audio lanes bill us per second, so they run on Premium model credits and come with a paid plan. A free account can look around; generating needs Starter or above.
What is in the studio
- Text to speech in dozens of voices and languages.
- Voice cloning from a sample you record or upload.
- Dubbing: translate a video's speech and re-voice it.
- Sound effects and ambience from a description.
- Lipsync: match a face in a video to a new track.
- Transcription with Whisper, for subtitles and search.
Audio and voice guides
- How to clone a voice and use it — Starter and up
- How to turn text into speech — Starter and up
- How to make a face match an audio track — Starter and up
- How to add subtitles to a video — Starter and up
- How to re-voice a video in another voice — Starter and up
- How to generate sound effects and ambience — Starter and up
- All tutorials