Clone my voice
LiveMake an AI copy of your own voice from a 15-60 second recording, with your recorded consent. Use it to translate live, translate files or read text.
Clone my voice
Example runAn example voice clone
A real run of this tool. Your own run replaces it.
Voice sample (a synthetic voice, not a real person)
The new voice reads
This is a brand new voice, cloned from a short sample. It can now read anything you write.
The new voice
Record your voice
Read the text below out loud for 15 to 60 seconds, or upload a clean recording of only you.
Read this out loud
Every morning I make a cup of coffee and look out of the window for a moment. Some days the street is quiet, and some days it is full of people hurrying to work. I like to plan my day slowly: first the things that matter most, then the small jobs that are easy to forget. In the evening I call a friend, cook something simple and read a few pages of a good book before I sleep.
- Find a quiet room and turn off music and fans.
- Only you should speak: samples with other voices are refused.
- Speak naturally, at your usual pace, a hand's width from the mic.
My voices
Only you can see and use these. Deleting one removes it everywhere.
Sign in to see your voices.
More voice tools
Each one is its own endpoint with its own price. Use one, or chain them.
LiveVoice TranslatorTalk in your language. Others hear theirs, in your own voice, in any app.Speech in $0.0206/min · voice out $0.066/minOpen
LiveLive transcribeSpeech to text as you speak, in many languages.$0.00846/minOpen
LiveTranslate an audio fileA recording in, the same words in another language and voice out.$0.3597/minOpen
LiveSpeak in my voiceType text and hear it in your own cloned voice.$0.39 per 1,000 charactersOpen
Clone my voice API
Send a sample and a consent recording; get a voice id (vc_...) that only your account can use.
https:/- GET
/Get the consent sentence to read aloudv1/ voices/ consent - GET
/Your voicesv1/ voices - DELETE
/Delete a voicev1/ voices/ {id}
Get an API key
Create a key in the console. It uses the same balance as the playground.
Create a keySend your first request
The same request the playground sends. Set OPENNAN_KEY to your key.
# 1. Get the consent sentence (read it aloud in English, record it) and its token curl https://api.opennan.com/v1/voices/consent -H "Authorization: Bearer $OPENNAN_KEY" # {"object": "voice.consent", "text": "...", "consent_token": "vct_...", "expires_at": "...", "terms": "..."} # 2. Clone: a 15-60 s sample of only you + you reading the sentence (2-30 s) curl https://api.opennan.com/v1/voices \ -H "Authorization: Bearer $OPENNAN_KEY" \ -F name="My voice" \ -F consent=true \ -F consent_token="vct_..." \ -F [email protected] \ -F [email protected] # Your voices curl https://api.opennan.com/v1/voices -H "Authorization: Bearer $OPENNAN_KEY" # Delete one curl -X DELETE https://api.opennan.com/v1/voices/vc_your_voice -H "Authorization: Bearer $OPENNAN_KEY"Read the result
The result comes back in the same response. The X-Usage-Cost-Usd header says what the call cost.
Errors and how to fix them
401Missing or wrong key
Send the header Authorization: Bearer with a key from the console.
402Balance too low
Add credit in Billing, then send the same call again.
400A value is not accepted
Read error.message: it names the field. Use a value from the parameter table.
429Too many requests
Wait a few seconds and try again, waiting longer after each 429.
Clone my voice: questions
Who can use my voice?
Only your account. Your voice id works only with your own keys and is never listed for anyone else.
What makes a good sample?
15 to 60 seconds of only you, speaking naturally in a quiet room. Samples with more than one speaker are refused.
How do I delete my voice?
Press Delete next to it under My voices, or call the delete endpoint with its id. It is removed everywhere it is kept.
What does Clone my voice cost?
$0.01296 per voice. If the consent check fails, nothing is made and you are not charged.
How do I call it?
Send POST https://api.opennan.com/v1/voices with your API key in the Authorization header. The answer comes back in the same response.
Am I charged when something fails?
No. A step that fails is not charged, and the reason is shown in plain words.
Can I use someone else's voice?
No. You can clone only your own voice, with a recording of you reading a consent sentence we give you. Voices are never shared between accounts.
Can my AI agent use it?
Yes, over the API. Have it read https://api.opennan.com/llms.txt to learn how.