Hazel
Mum voice: patient, then suddenly not
Cloning
Voice Cloning — Your Own Voice, From a Recorded Consent Statement
Voice cloning is open, and it works one way only: you read a short consent statement aloud — your name, today's date, and that you agree to this recording being used as your voice — and that recording becomes the voice. There is no separate sample to upload and no way to submit someone else's audio, because the consent and the voice are the same file. It is a reading voice: it says the words and follows line speed, but it does not act out emotions or directions the way the library characters do.
At a glance
- What it is
- A free AI voice generator and text-to-speech workbench built for scripts: it works out who is speaking, gives every character their own voice, lets you direct the emotion line by line and exports a finished mix — a full-cast audio drama rather than one narrator reading every part.
- What you paste in
- A script, pasted as text. Screenplay format, “Name: line” dialogue and ordinary prose with dialogue tags are all read as written, and so are the em-dash conventions used in Spanish, French, Portuguese and Russian. A note in brackets at the start of a line, or a line that is entirely inside brackets, becomes that line's acting direction: it is performed rather than spoken, and you can edit it in the line list. There is no file import, so paste the text instead of attaching a document.
- What you get back
- One mixed MP3 on every plan. SRT subtitles from Plus upward — written from your script rather than transcribed from the audio, so names are spelled right and the timings already line up. Per-character stems, one full-length track per character plus the mix, come as a ZIP on Pro. No WAV export.
- Cast and voices
- 40 library characters, each with a portrait, a persona and a sample. Behind them sit 10 base voices — 4 female, 5 male, 1 androgynous — and the same 10 serve every language. Inside one project no two characters are given the same base voice until all 10 are taken, so a scene of up to 10 speakers separates cleanly; past that, two characters share a voice and are told apart by persona and by the direction each line carries. You choose the character, not the base voice. You can also clone your own voice by reading a short consent statement aloud — up to 3 per account — and give it to any character; a cloned voice reads in all 9 languages and follows line speed, but does not act out emotions or directions.
- Languages
- 9: English, 简体中文, 日本語, 한국어, Deutsch, Français, Español, Português, Русский. Every character performs in all of them — a character is a persona, not one recorded take — and a project's language is fixed when the project is created. Outside English you get the language's common accent; regional accents cannot be picked and are not promised. We have not had native speakers audition every language, so run your own lines through it before you commit.
- Emotion and direction
- Every line is performed by an AI voice actor working from a written direction, so the 7 emotions (neutral, happy, sad, angry, fear, whisper, excited) are acted rather than faked with settings. A resting emotion per character is available on every plan; overriding emotion line by line is Pro only, and 5-step speed control (0.75×–1.25×) comes with Plus and Pro. Regenerating a line gives a genuinely different take in the same voice, and editing one line re-synthesises only that line.
- Price and open beta
- A credit is one character of script, and credits are spent only when you download — generating and previewing cost nothing, within a ceiling of 30 lines per 24 hours on Free and up to 2,000 on Pro. Free is a one-time pot of 4,500 credits, about 5 minutes of finished audio, with 2 cast members per project. Paid plans are Basic $5, Plus $19, Pro $29 a month, 10% off yearly. Payments are not live yet: during the open beta every account gets the full Pro feature set at no cost, but a commercial licence still comes with a paid plan once plans open.
- What it cannot do yet
- Voice cloning covers your own voice only, and a cloned voice reads the words without acting out emotions or directions. There is no file import, no WAV export, no pronunciation dictionary, no pitch control, and no way to pick a specific base voice or a regional accent. No language has real child voices: child parts are played by adult performers, the way animation has always done it. Characters live inside one project and do not carry over to the next.
Voices to try it on
Orrin
Old man on a porch who remembers the flood
Tess
Australian lead with a flat, dry delivery
Sable
Noir detective narrating her own bad decisions
Juno
Podcast host who thinks out loud and never reads a script
Dorian
Audiobook baritone for literary fiction and slow reveals
Quill
YouTube explainer voice that never sounds bored
Kestrel
Low, weary swordswoman who has already lost this war once
What it does
One recording, about ten seconds
The statement takes eight to fifteen seconds to read. Record it in the browser — a phone works — or upload a recording of yourself reading the same statement. Recordings must be between 4 and 30 seconds and at most 10 MB.
The consent is the voice
We do not accept a random clip. The recording you clone from is the statement itself, which ties every cloned voice on the service to a specific person saying, on a specific day, that they agree. You also confirm two things before recording: that the voice is your own, and that you are 18 or older.
Reads all nine languages
A clone recorded in one language can read lines in any of the nine the studio supports — an English recording can read Japanese. How natural that sounds varies from voice to voice, so listen to a few lines before you commit a whole script to it.
Words and speed, not acting
A cloned voice reads the text as written and follows the line speed setting. Emotions and bracketed acting directions have no effect on it; the studio says so on any character that uses a clone. If a part needs performing, cast a library character for it.
Up to 3 voices per account
During the open beta cloning is available on every plan. A cloned line is counted like any other: synthesis counts toward your daily line limit, and downloads use credits exactly as they do for library voices.
Delete it whenever you like
Deleting a clone in the studio removes the recording and every line that was generated with it. Characters that used it go back to their library voice, and those lines need generating again.
How to use it
- Confirm the two basics
Tick that the voice is your own and that you are 18 or older. The rules on who may not be cloned are linked right there.
- Get your statement
Enter your name and a display name for the voice. The studio shows the consent statement to read, with today's date filled in.
- Record it
Read the statement once, in a quiet room, at the pace and tone you want to hear back. Play it back and re-record if it is noisy. Or upload a file of yourself reading the same statement.
- Give it to a character
Pick the clone from the voice menu on a character card, the same way you would pick a library character, then generate a line or two to check it.
- Delete it when you are done
Remove the clone from the studio at any time; its recording and the lines made with it go with it.
Why the recording has to be the consent statement
Most cloning products have a clause in their terms saying you must have permission. A clause cannot be checked: the platform has no idea whether the person in the recording agreed, and after the fact there is nothing to look at.
Here the only audio a clone can be made from is a person reading, in their own voice, a statement that names them, gives the date and says they agree. That is a little friction — about ten seconds — and it means every cloned voice comes with its own evidence of consent rather than a ticked box.
It also filters out the uses that should not happen. A podcast clip, a film scene or a voicemail cannot be turned into a clone, because none of them is that person reading the statement.
What we will not clone
Public figures and performers, including under a parody or research framing. A synthetic recording of an identifiable person is indistinguishable from a real one once it leaves your project, and no disclaimer travels with an audio file.
Minors, under any circumstances, including with parental consent. A cloned voice of an identifiable child is a tool for impersonating that child, and no creative requirement justifies creating one.
Deceased people. This is the request we handle most often and most carefully, usually from someone who wants to hear a parent or grandparent again. Consent cannot be obtained, and in most jurisdictions an estate cannot grant it retroactively. What we can help with is casting a voice that sits in the register you remember and using it as a character rather than as an impersonation.
Where the recording goes
No voice model is trained. Your recording is the voice: it is stored on our servers, and each time a line is synthesised it is handed to our speech synthesis provider through a link that stops working after ten minutes, together with the text of the statement and the line to be read.
It stays until you delete it. Deleting the clone deletes the recording and the audio generated with it. If you believe someone has cloned your voice without your consent, contact us and we will remove it; you do not need to hold the account that made it.
Getting a good recording
The clone takes its sound from those few seconds, so they matter more than anything else. A quiet, soft room beats an expensive microphone in a kitchen. Keep the same distance from the microphone throughout, and read at the pace and in the tone you want to hear back.
Then test it on a line from your actual script rather than on the statement, which it will always handle well. If it sounds off, delete it and record again — the statement is short enough that a second take costs almost nothing.
Frequently asked questions
Can I clone my own voice?
Yes — that is the only thing cloning here does. You read the consent statement once, and that recording becomes a voice you can give to any character in your projects.
Can I clone a friend's voice for my project?
Not from your account. Every clone has to be the account holder's own voice, read in their own words. Your friend can sign up and clone their own voice, but clones stay in the account that recorded them.
Can I upload an existing recording, like a podcast clip?
No. The only audio accepted is you reading the consent statement the studio gives you. An upload is allowed, but it must be a recording of that same statement in your own voice.
Does a cloned voice do emotions?
No. It reads the words and follows line speed, but emotion settings and bracketed acting directions have no effect on it. For lines that need acting, cast a library character.
Which languages can my clone speak?
All nine the studio supports, not only the one you recorded in. How natural it sounds in another language varies, so listen before you commit a script to it.
How many voices can I clone, and what does it cost?
Up to 3 per account. During the open beta cloning is available on every plan, and cloned lines use the same allowances as any other line: they count toward your daily synthesis limit, and downloads use credits as usual.
Who can delete a clone?
You can, at any time, from the studio. The person whose voice it is can also ask us to remove it, whether or not they hold the account. Deleting removes the recording and the audio generated with it.
Can I clone a character from a game or film?
No. That is a performer's voice, and cloning it is prohibited regardless of how transformative the project is. Cast a voice in a similar register instead — it is legal, it works, and it is what most people end up preferring anyway.
Cast your first scene tonight
Paste a script, let CastDub assign a voice to every character, and export a finished drama.
Create for freeNo credit card. Free gives you a one-time pot of credits.