Google DeepMind

Gemini 2.5 Flash TTS

Generally availableProprietary33K context

Summary

Gemini 2.5 Flash TTS is a proprietary speech model from Google DeepMind, released on 30 Sept 2025. It accepts text and generates audio, with a 33K-token context window and up to 16K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $0.50 per million input tokens and $10 per million output tokens (Google Vertex AI), across 1 provider we track.

Speech generation model for controllable voice, narration, and audio delivery

Last verified 4 Oct 2026. Every figure on this page links to its source.

Specifications

DeveloperGoogle DeepMind
Release date30 Sept 2025 [models.dev]
StatusGenerally available [models.dev]
WeightsProprietary (API only) [models.dev]
Context window33K (32,768 tokens) [models.dev]
Max output16K tokens [models.dev]
Knowledge cutoffJan 2025 [models.dev]
InputText [models.dev]
OutputAudio [models.dev]
Reasoning modeNo [models.dev]
Tool callingNo [models.dev]

Gemini 2.5 Flash TTS API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
Google Vertex AI
gemini-2.5-flash-tts
$0.50$10–33Kmodels.dev, 4 Oct 2026

Frequently asked questions

What is the context window of Gemini 2.5 Flash TTS?

Gemini 2.5 Flash TTS has a context window of 32,768 tokens (33K) and can generate up to 16,384 tokens in a single response, according to models.dev.

How much does the Gemini 2.5 Flash TTS API cost?

Gemini 2.5 Flash TTS is listed from $0.50 per million input tokens and $10 per million output tokens (Google Vertex AI). Prices last verified 4 Oct 2026.

Is Gemini 2.5 Flash TTS open source?

No. Gemini 2.5 Flash TTS is a proprietary model; Google DeepMind has not released its weights. It is available through APIs including Google Vertex AI.

When was Gemini 2.5 Flash TTS released?

Google DeepMind released Gemini 2.5 Flash TTS on 30 Sept 2025, according to models.dev.

Change history

No changes detected since we started tracking this model. We re-check every source daily.

Sources