Google DeepMind

Gemini 2.5 Pro Preview TTS

Generally availableProprietary8K context

Summary

Gemini 2.5 Pro Preview TTS is a proprietary speech model from Google DeepMind, released on 1 May 2025. It accepts text and generates audio, with a 8K-token context window and up to 16K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $1 per million input tokens and $20 per million output tokens (Gemini API), 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 date1 May 2025 [models.dev]
StatusGenerally available [models.dev]
WeightsProprietary (API only) [models.dev]
Context window8K (8,192 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 Pro Preview TTS API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
Gemini API
gemini-2.5-pro-preview-tts
$1$20–8Kmodels.dev, 4 Oct 2026

Frequently asked questions

What is the context window of Gemini 2.5 Pro Preview TTS?

Gemini 2.5 Pro Preview TTS has a context window of 8,192 tokens (8K) and can generate up to 16,384 tokens in a single response, according to models.dev.

How much does the Gemini 2.5 Pro Preview TTS API cost?

Through Gemini API, Gemini 2.5 Pro Preview TTS costs $1 per million input tokens and $20 per million output tokens. Prices last verified 4 Oct 2026.

Is Gemini 2.5 Pro Preview TTS open source?

No. Gemini 2.5 Pro Preview TTS is a proprietary model; Google DeepMind has not released its weights. It is available through APIs including Gemini API.

When was Gemini 2.5 Pro Preview TTS released?

Google DeepMind released Gemini 2.5 Pro Preview TTS on 1 May 2025, according to models.dev.

Change history

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

Sources