If you have ever needed a quick voiceover for a demo video, a podcast intro, or a language-learning clip, you know the usual options: record it yourself, hire a voice actor, or wrestle with a robotic-sounding TTS engine. I wanted something faster and more expressive, so I have been using GeminiTTS, an online text-to-speech studio powered by Gemini 3.8 TTS.
What GeminiTTS does
GeminiTTS is a browser-based tool: paste your script, choose a voice, and generate audio you can play back or download as WAV. There is nothing to install and no API key to manage.
Key features:
- Two models – Gemini 3.8 Flash for expressive, natural delivery, and Flash Lite for faster drafts when you are iterating on a script.
- 30 preset voices – a wide range of tones, from calm narration to energetic promo reads.
- Single voice or two-speaker dialogue – write a conversation between two speakers and get one audio file back. Great for podcast-style explainers, interview mockups, or language lessons.
- Delivery controls – adjust accent, style, and pace, and add short vocal cues to shape how lines are read.
- Library + WAV download – every generation is saved to your library so you can replay or download it later.
Why two-speaker dialogue matters
Most TTS tools give you one voice at a time. If you want a dialogue, you end up generating separate clips and stitching them in an audio editor. With Gemini 3.8 TTS in GeminiTTS, you write the dialogue once, assign speakers, and the model handles turn-taking and pacing. For quick prototypes of podcasts, explainer videos, or app onboarding flows, that saves a surprising amount of time.
A simple workflow
- Open geminitts.app and sign in.
- Pick Flash Lite while drafting your script so iterations are quick.
- Choose a voice (or two, for dialogue) and tweak accent, style, and pace.
- Add short vocal cues where you want emphasis or a change of tone.
- Switch to Flash for the final take, then download the WAV.
Use cases
- Voiceovers for product demos and side-project launch videos
- Podcast intros, outros, and two-host explainer segments
- Language-learning dialogues
- Accessibility: turning blog posts into audio
- Placeholder audio for games and prototypes
Pricing
GeminiTTS is freemium: new accounts receive 20 free starter credits, which is enough to try both models and test the dialogue mode before deciding whether you need more.
Note
GeminiTTS is an independent app built on top of Gemini 3.8 TTS — it is not a Google product.
If you are building side projects and need natural-sounding text to speech online without setting up an API pipeline, give GeminiTTS a try and let me know what you make with it in the comments.
Top comments (0)