Turn text into a natural voiceover

Choose from voice models made for narration, characters and ads. Many let you set the mood, speed or language, and the audio is ready to drop into a video or a Talking Avatar.

Make a voiceover How it works

From 2 credits per minute of audio
30 free credits when you sign up · no card needed
A run that fails is refunded automatically

You add: Your script
You get: An audio file of the voice reading it
Usually ready in: about 10 sec
Starts at: 2 credits per minute of audio

How it works

1
Paste or type your script.
2
Choose a model and a voice, plus speed or mood if it offers them.
3
Generate, listen and download.

Make a voiceover

Tips for better results

Write numbers and abbreviations the way they should be said.
Use punctuation for pauses: commas for short ones, full stops for longer ones.
Try two or three voices on the first line before making the whole script.

Great for

Video narration
Voices for talking avatars
Ads, podcasts and audiobooks
UGC ads

Models you can use

9 models

PopNow starts you on Gemini 3.8 Flash TTS. Switch to another model in the generator any time; each one shows its price before you run it.

Questions people ask

Which languages can it speak?

Most voice models speak many languages, including English, Spanish, German, French, Japanese and Chinese. The voice list in the generator shows what each one supports.

Can I make it sound excited or calm?

Yes. Some models take cues in the script, like [laughing], and others offer voices and emotion settings for different moods.

Can I turn the voiceover into a talking video?

Yes. Use the audio in Talking Avatar with a portrait, or in Lip Sync with a video you already have.

How much does Text to Speech cost?

Text to Speech starts at 2 credits per minute of audio. The generator shows the exact price before you run it, and a run that fails is refunded automatically. New accounts get 30 free credits, enough to try it.