Gemini TTS

Gemini 3.1 TTS is a web-based AI text-to-speech generator for creators, developers, and teams that need natural, emotion-rich narration, voiceovers, and conversational dialogue.

Key capabilities include:

• 70+ languages with multilingual speech generation and expressive controls
• 30+ built-in voice profiles with selectable speaker settings and tonal characteristics
• 200+ expressive audio tags to control pace, tone, emotion, whispers, laughter, and pauses directly in the script
• Multi-speaker dialogue generation in a single render, plus voice and speed controls.**

Pricing: Paid, one-time credit packs starting at $9.90 for 99 credits. Other packs include $29.90 for 330 credits, $49.90 for 600 credits, and $99.90 for 1,250 credits. Credits do not expire, and there is no subscription.

Notable for combining Google’s Gemini 3.1 Flash TTS model with fine-grained, script-level expressivity controls and built-in multi-speaker output, making it useful for audiobooks, podcasts, interactive fiction, and video narration without external audio editing.