113 voices · 24 languages · Vietnamese included
Turn your text into a natural voice in seconds.
Voxmint is an AI voice generator and text to speech tool with 113 voices in 24 languages, for voice overs, videos, lessons and stories. Pick a voice or describe a new one, type your words, download the audio. No microphone, no studio.
Try it
1. Pick a voice
Your words and voice come with you when you create your free account.
See it in 30 seconds
Pick a voice, type, download. Turn the sound on to hear each voice.
More than voices
The rest of your audio, in the same place and from the same credits.
Music
Songs up to 4 minutes from a style and your own English lyrics, or instrumentals.
“Warm indie pop, gentle female vocal, acoustic guitar and soft drums, sunny morning mood”
Sound effects
Describe a sound and get a clip of 1 to 30 seconds.
“An old wooden door creaks open slowly, then slams shut in an empty hallway”
Dialogue
Paste a script, give each speaker a voice, download one file.
“Maya: Did you hear back from the studio yet? Owen: They loved the demo. They want the whole album by March. Maya: [laughing] March? We haven't even named the band.”
Speech to text
Turn audio or video into an editable transcript, then download it as text or subtitles.
For 10,000 years, this valley has kept its secrets.
Have a finished track? You can also split music into vocals, drums, bass and more.
What people make with Voxmint
Videos & social
Voice-overs for YouTube, TikTok and Reels without recording yourself.
Ads & promotions
Shop announcements and radio-style ads in minutes.
Stories & audiobooks
Read a chapter aloud in a calm, warm voice.
Lessons & training
Clear narration for courses, slides and how-to videos.
Captions included
Every clip can come with captions timed to each word.
24 languages
The same script in Vietnamese, English and many more.
Hear the voices
Straight from the model. No editing, no retakes.
Hollis
English · Documentary narrator
“For ten thousand years, this valley has kept its secrets.”
Linh
Vietnamese · Hanoi · TV presenter
“Xin chào quý vị. Hà Nội những ngày cuối thu, trời se lạnh, hoa sữa nồng nàn trên khắp các con phố cổ.”
Camille
French · Paris · Lifestyle & advertising
“Ce matin, on file au marché, on prend un café en terrasse…”
Lucía
Spanish · Warm & expressive
“Hola, bienvenidos. Hoy vamos a empezar por el principio.”
Three steps, about a minute
Pick a voice
Press play to hear any voice before you choose it.
Type your words
Paste a line or a whole script. Most voices also take emotion tags like [laughing].
Download the audio
It starts playing in seconds. Download it when it sounds right.
Can't find the right voice? Describe one.
Write who should speak, in plain words: age, mood, accent. Voxmint makes that voice for you.
Design a voiceVoice description
“A deep male documentary narrator, late forties, slow and deliberate, warm and authoritative.”
Start free. Pay only when you need more.
Free gives you 30,000 characters a month for personal use. Paid plans start at $5 a month for about 5.6 hours of speech and include a commercial licence.
Text to speech FAQ
Which languages can it speak?
24 languages, including Vietnamese, English, Chinese, Japanese, Spanish and French, with 113 ready-made voices.
Is it free?
Yes, to start. The Free plan gives you 30,000 characters a month with every voice, for personal, non-commercial use. No card needed.
How much does it cost after the free plan?
Paid plans start at $5 a month for about 5.6 hours of speech. You can also buy one-time credit packs, with or without a plan.
Can I use the audio commercially?
Yes, on any paid plan or after buying any character pack, including in monetised videos, ads and apps. The Free plan is for personal use only.
Do I need to install anything?
No. Voxmint runs in your browser, on a phone or a computer.
How do I get the audio?
Press Download when it sounds right. You can also download captions with the timing of every word.
Can I make a voice of my own?
Yes. Describe the voice you want in a sentence (age, mood, accent) and Voxmint makes it.
Can it clone my voice?
No. Voxmint doesn't copy voices from recordings. Pick a ready-made voice or describe a new one in words. Our voice policy explains how the voices are made.
Who runs Voxmint?
Voxmint is a small independent product, operated by Linh Vu, trading as Voxmint, Vietnam. More about Voxmint
Hear every voice in your language
- Chinese text to speech
- Japanese text to speech
- Korean text to speech
- Spanish text to speech
- Portuguese text to speech
- Hindi text to speech
- Vietnamese text to speech
- French text to speech
- English text to speech
- German text to speech
- Arabic text to speech
- Indonesian text to speech
- Italian text to speech
- Russian text to speech
- Turkish text to speech
- All languages