Gemini 3.8 text-to-speech models now available on AI Gateway
By Steven Van ·
Flash-Lite suits high-volume narration while Flash adds natural-language voice and character direction, both with per-request cost tracking.
Two Gemini 3.8 text-to-speech models from Google are now available through Vercel's AI Gateway. Both google/gemini-3.8-flash-lite-tts and google/gemini-3.8-flash-tts convert text to speech in more than 100 languages, with support for long-form narration, control over delivery, and two-speaker dialogue.
- Flash-Lite TTS is suited to high-volume speech generation, with controls for tone, pacing, and line-by-line delivery.
- Flash TTS adds voice and character design through natural-language prompts, including acting cues, accents, and conversational reactions.
Both models can be tried in their respective playgrounds. Requests go through the same AI Gateway API as Vercel's other models, with usage and cost tracking per request, configurable routing rules, and the option to bring your own provider key. See the speech quickstart for setup details.
Vercel
The platform for frontend developers — deploy, preview, and scale web apps and AI agents with zero config.
View Vercel →