AI Voice Workspace
Text to speech, your own cloned or designed voices, audiobooks and transcripts.
Clone a voice from a short recording or describe a new one, then have it read anything β a script, an article, a whole book as MP3 chapters. Preset voices speak ten languages, your own voices seven. Recordings and videos become transcripts with times and speakers. Your own voices also speak in the dubbing, voiceover and talking-photo use cases.
Skills available now
AI voice cloning
Clone a voice from 10β60 seconds of speech and have it read anything.
AI voice design
Describe a voice in a sentence and get a new one.
Text to audiobook
A novel, EPUB or PDF into MP3 chapters, in any of your voices.
Audio & video to text
Timestamps and speakers; SRT, VTT or Word; meeting minutes.
AI Text to Speech
Turn text into natural speech in 10 languages β pick a voice, get an audio file for videos, lessons, podcasts and product demos.
Which AI voice tool to use
Turn text into speech
Paste up to 3,000 characters at a time, pick a voice and download the audio, in any of 10 languages: for videos, lessons, podcasts and product demos.
Make a voice of your own
Describe a voice by its age, tone, pace and mood and get a new one, with no recording needed; hear it before you keep it. Your own voices read seven languages.
Voiceover and dubbing for video
Add a voiceover, captions and music to a clip you already have. To reach another language, dub a video: what is said is translated to match the timing and read over the original background sound. For a script alone, a multilingual voiceover translates it and reads it aloud.
Add voiceover to videoAI video dubbingMultilingual voiceover
AI models
Where this model is used