AI Voice & Speech Studio
VocaTTS — a studio for making AI voices and putting them to work
Clone your own voice or design a brand-new one from a few lines of description. Then use it to read video scripts, podcasts, lessons, subtitles and dubs — all from your browser.
Prefer not to use your real voice? Design one from a description instead.
- voices ready to use
- 4,028
- languages covered
- 147
- voice providers
- 4
Voice Cloning: your voice, reading any script
Record 10–30 seconds of natural speech, add a short consent statement in the same voice, and VocaTTS builds an AI version of it. After that, changing a script no longer means booking another recording session.
- 10–30 second sample, recorded in the browser or uploaded
- A consent recording by the same speaker is required
- Use the cloned voice in Text to Speech, SRT and multi-speaker projects
Voice Design: describe it in words, get a new voice
No recording needed. Write down the voice you want — age, accent, timbre, pace, mood — and get an original synthetic voice saved to your account for reuse.
“A warm, friendly female voice in her late twenties, clear and unhurried, suited to educational videos.”
Text to speech built for creators
- Multi-segment mode: every segment becomes its own audio file
- Pitch, speed, volume and speaking styles on supported voices
- Emotion tags for Gemini voices, such as [excited] at the start of a line
A voice library with real numbers
From subtitles to a finished dub
SRT to Audio
Upload an .srt file and get narration that follows the timeline, with speed adjusted to fit each line.
Voice your subtitlesMulti-Speaker
Give every character a voice, add pauses between lines and export one dialogue track.
Build a dialogueAI Dubbing
Translate subtitles into another language, assign voices to speakers [A], [B] and generate a timed dub.
Start a dub
What people make with it
YouTube & short video
Narrate in your own voice, then edit the text and regenerate instead of re-recording.
Podcasts & dialogue
Two hosts or a full cast — each speaker gets a voice in the same file.
Lessons & e-learning
Clear, evenly paced narration for slides, tutorials and course material.
Audiobooks & documents
Turn PDF, DOCX and EPUB files into audio to listen on the go.
Practice speaking with Gemini, out loud
A real-time voice session: you talk, Gemini answers in speech. Modes for English practice, mock interviews and travel situations.
One credit balance for every tool
Plans include credits you can spend on text to speech, subtitles, dubbing and documents. Custom voices (cloned or designed) start with the Basic plan. Pay once by card, PayPal or SePay — nothing renews automatically.
Frequently Asked Questions
Q: What is VocaTTS?
A: VocaTTS is a browser-based studio for creating AI voices and using them. You can clone your own voice, design a new voice from a description, or pick from the voice library, then generate narration, subtitle voiceovers, multi-speaker dialogue and dubs.
Q: Do I need a paid plan to create a custom voice?
A: Yes. Cloned and designed voices start with the Basic plan, which includes three custom voice slots. Premium and Studio include five. Stock voices in the library can be used without a custom voice.
Q: Can I use my cloned voice for subtitles and dialogue?
A: Yes. A custom voice appears under “My voices” in every voice picker, so you can use it in Text to Speech, SRT to Audio and Multi-Speaker projects.
Q: Which languages can I generate?
A: It depends on the voice. Native Google and Azure voices cover dozens of languages, and Gemini's multilingual voices support well over a hundred. The Voice Library lists every voice by language.
Q: How do I pay?
A: By credit or debit card or PayPal (cards are processed by PayPal, no account needed), or with SePay (VietQR and bank transfer) from a Vietnamese bank. Plans are one-time payments and do not renew automatically.
Your first voice is a few minutes away
Record a short sample or write a short description, then use that voice in your next video.