Gemini 3.1 Flash TTS

Text-to-speech model: text in, audio out. Input $1.00 (text), output $20.00 (audio); batch $0.50 / $10.00. Audio tokens are billed at 25 tokens per second of audio. Until 2026-10-06 Google stated "No shutdown date announced" and the status was held at preview. On the 2026-10-07 read Google's deprecations table publishes a shutdown date of November 17, 2026 for this endpoint (row not grey, so it is still running); status is therefore deprecated and retires_on carries that date. Google publishes shutdown dates as "the earliest possible dates on which a model might be retired". Until 2026-09-22 Google named no replacement; that day's deprecations table added 'gemini-3.8-flash-tts or gemini-3.8-flash-lite-tts'. The replacement field holds one id and carries the first-named, gemini-3.8-flash-tts, in the table's own order - but both are first-party migration targets, and the same day's release note describes gemini-3.8-flash-lite-tts as 'built to replace gemini-3.1-flash-tts-preview'. Both successors are cheaper than this model on the rates in force through 2026-12-31 (output $9.00 and $6.00 against $20.00). Released February 26, 2026, the date in the Release date column of Google's deprecations table. Until 2026-09-24 that table listed this id in two rows, one dated February 26, 2026 carrying the replacement and one dated April 13, 2026 with none, and the released field held April 13; by the 2026-09-25 read Google had removed the April 13 row, leaving February 26 as the only date it publishes. Google's current models page publishes no input/output token limits for this endpoint (read 2026-08-19), so context_window and max_output_tokens are null rather than carried over from a page that no longer states them. Lifecycle read first-party from Google's deprecations table on 2026-08-19 and re-read 2026-09-25.

Source: Google official documentation ↗

Explore more

Gemini 3.1 Flash TTS — questions & answers