Gemini TTS
Online text to speech with 130 languages, 30+ voices and 200+ audio tags.
- SI Score
- 74/100
- Pricing
- One-Time Purchase
- Free plan
- Not confirmed
- Sign-up required
- Not confirmed
Ask SI about Gemini TTS
Answers use saved listing facts and recorded sources.Homepage screenshot
What it does
Gemini TTS turns text into speech in a browser workspace. It is built on Google's Gemini text-to-speech models and offers 130 languages, 30+ voices and 200+ expressive audio tags. You can create voiceovers, narration and multi-speaker dialogue, then download the audio as MP3 or WAV.
Gemini TTS is a browser tool for turning scripts into speech. You type or paste text, pick a model such as Gemini 3.8 Flash TTS or Gemini 2.5 Pro TTS, choose a voice, and add tags like [excitement] or [whispers] to shape delivery. Multi-speaker dialogue is generated in one pass, and audio downloads as MP3 or WAV. The site says it supports 130 languages and 30+ voices. Pricing is one-time credit packs: Base at $9.9 for 99 credits, Pro at $29.9 for 330 credits, Ultimate at $49.9 for 600 credits, and Creator at $99.9 for 1250 credits. Credits do not expire. The pricing FAQ says 1 credit is about 1,000 characters on Gemini 2.5 Flash, while Gemini 2.5 Pro uses 2 credits per 1,000 characters. Text under 1,000 characters is still billed as 1,000 characters per request. The site does not state whether an API is available, so that remains unknown.
- 200+ audio tags for emotion, pace and non-verbal sounds
- Multi-speaker dialogue generated in one pass
- 130 languages with accent and pacing control
- Credits are one-time packs, not a recurring subscription
- Text under 1,000 characters is billed as 1,000 characters per request
- No API access is stated on the site