Voice Cloning creates a voice from recordings of one speaker. The new voice appears in your voice list and can be used in Text to Speech and Audio Studio next to the library voices. It suits a consistent brand voice for videos, courses and ads, or narrating your own content in your own voice.
Requirements
- One to five recordings of the same speaker.
- Formats: MP3, WAV, M4A, AAC or OGG, up to 50 MB per recording.
- You must have the right to use the voice: clone your own voice or one you have permission to use.
How to clone a voice
- Open Clone A Voice and click New Clone.
- Upload the recordings.
- Give the voice a name. This is how it appears in your voice list.
- Click Clone Voice. The voice is then ready to use.
Get the best recordings
- Quiet room: background noise ends up in the cloned voice.
- Good microphone: an external or headset microphone works better than a laptop microphone.
- Same setup every time: do not change the microphone or room between samples.
- One speaker, clear speech, no music. Longer, cleaner recordings give a closer result.
Good to know
- How many voices you can clone depends on your plan. The clone page shows how many are left.
- A cloned voice that is not used for text to speech for 7 days in a row is deleted automatically and permanently, after a warning by email.
- Generating speech with a cloned voice is charged like any Text to Speech generation; see the pricing page.
- If the clone sounds noisy, lower Similarity in the voice settings or clone again from cleaner recordings.
- Clones are created in the web app, then used by id through the API or MCP like any other voice.
Details are in the Voice Cloning documentation, or visit the Voice Cloning page.