Gemini 3.1 Flash TTS Preview

Text to speech Google Verified Deprecated Shuts down Dec 18, 2026 Recommended instead: Gemini 3.8 Flash TTS or Gemini 3.8 Flash Lite TTS Released Feb 26, 2026

Gemini 3.1 Flash TTS preview is a text-to-speech model for low-latency, controllable speech generation, supporting single-speaker and multi-speaker audio. It embeds stage directions in plain text, whereas Gemini 3.8 Flash TTS separates style instructions from the transcript. Summary written by AI Index from Google’s own pages.

Prices

1 offering · prices as listed
Gemini API (opens in a new tab) Official Preview Global · USD gemini-3.1-flash-tts-preview
Conditions/ 1M tokensInputOutput
Text tokens Standard $1.00—
Audio tokens —$20.00
Text tokensBatch $0.50—
Audio tokensBatch —$10.00

Prices from Gemini API pricing (opens in a new tab) (checked Nov 8, 2026)

Standard: the price a request with no conditions pays (the headline price elsewhere on the site).

Details

Model ID

Not stated on Google’s pages: streaming, max input.

Cited scores

From third-party leaderboards, not measured by us

No cited leaderboard covers speech synthesis yet. We will cite one when its license allows.

  1. Preview → Deprecated

Sources

Google’s official policies: data use, privacy, terms →

Google · United States · ai.google.dev

Snapshots, the same family and other models from this provider