Text to speech and voice cloning online
Paste up to 10,000 characters and pick one of hundreds of voices, or clone your own voice from a recording. The price in tokens is shown before you pay.
3 free tries, no sign-up
Emotion tags for MiniMax
Tap a tag or drag it into the text. In the text it stays in English: that's what the model reads.
Voice
You have 3 free tries
Text up to 200 characters
How to turn text into speech
- 1
Paste the text
Paste or type up to 10,000 characters. Tags like [excited] or (laughs) set the emotion right in the text.
- 2
Pick a voice and pay
Listen to the samples, choose a voice and set the style. The price is shown before you pay: from about 2 tokens per minute of speech. One-time payment from $2.99, no subscription.
- 3
Listen and download
Play the voice-over and save the file. It stays in your account history.
What you get
Four engines in one place
OpenAI, ElevenLabs v4, Qwen 3 and MiniMax. Each has its own character, so you can pick the sound you need.
Samples before you pay
Every voice has a short sample, so you hear it before spending a token.
Emotion and style
Style presets for OpenAI voices, emotion, speed and pitch for MiniMax, tags in the text for ElevenLabs.
Thousands of ElevenLabs voices
Search the library and the community by language, gender, age, accent and use case.
Price before you pay
The cost is counted from your text and the voice you picked, and shown in tokens.
Clone your own voice
Record about a minute of speech or upload a file, and voice any text in your own voice. Cloning costs 1 token with Qwen 3 and 180 with MiniMax.
Natural voices for any text
Text to speech turns an article, a script, a lesson or a message into audio you can play or publish. Here you choose among voices from four engines and can hear each one first.
Paste the text, listen to a few samples and set the delivery: a calm teacher, a cheerful host, a whisper. ElevenLabs v4 and MiniMax also read emotion tags written inside the text, such as [laughs] or (sighs).
Short texts cost a few tokens. A long article costs more, and the exact price is shown before you pay.
Frequently asked questions
More tools
Get a summary right in your browserPaste a YouTube, TikTok or Instagram link and get key points with timestamps in a couple of minutes. No app needed.Get the text of a video right in your browserPaste a YouTube, TikTok or Instagram link and get the transcript with timestamps. No app needed.Turn a voice message into text in your browserUpload an audio file or record your voice and get the transcript with timestamps. No app needed.Download a video right in your browserPaste a YouTube, TikTok or Instagram link and save it as MP4 up to 4K or MP3, without a watermark. No app needed.Add subtitles to a video in your browserUpload a clip or paste a link, choose a style and get a video with subtitles, translated if you need.Translate a voice message in the speaker's voiceUpload a recording or speak into the microphone, pick a language and hear the translation in the same voice. No app needed.Voice changer for audio and videoSwap the voice in a recording or a video for another one and keep the delivery. Thousands of ElevenLabs voices, no app needed.Video translator and dubbingTranslate a video into another language and keep the speaker's voice. Fast dubbing or a lip-synced version, no app needed.More in the VocaLingo app
Clone your own voice, translate audio and video, add subtitles and summarize recordings. The same tokens work in the app.
Point your phone camera here
Opens the App Store or Google Play
Also on iPhoneAndroid · web version