Oossa

Google adds Gemini 3.8 Flash TTS models to its API

Google released two new text‑to‑speech models, Gemini 3.8 Flash TTS and Flash‑Lite TTS, for general availability on its Gemini API.

NoteOossa1 min read

Google announced that the Gemini API now offers two new text‑to‑speech models. Gemini 3.8 Flash TTS is a high‑quality, studio‑like voice model, while Gemini 3.8 Flash‑Lite TTS is a faster, cheaper version aimed at real‑time voice agents and high‑volume use. Both are accessed through the new /v1beta/voices endpoint. The update gives developers a richer voice library with over 150 built‑in and custom voices.

Why it matters

Developers can now add more natural, scalable speech to apps without building their own voice models.

Was this article useful?
Share

Read next

Oossa · Newsletter

The week in AI, explained

Every Monday: the stories worth knowing, in plain language. Free, no spam.

Sources & references

#SourceOutletDateKey takeaway
1ai.google.dev: April 1, 2026 ↗Google Gemini APISep 29, 2026Memperkenalkan tingkat inferensi Flex dan Priority baru, yang menawarkan lebih banyak opsi untuk mengoptimalkan biaya atau latensi.

1 sources

Last updated: ·Markdown·llms.txt