Gemini 3.1 Flash TTS Preview
Summary
Gemini 3.1 Flash TTS Preview is a proprietary speech model from Google DeepMind, released on 15 Apr 2026. 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.
Low-latency speech generation with steerable prompts and expressive audio tags
Last verified 4 Oct 2026. Every figure on this page links to its source.
Specifications
| Developer | Google DeepMind |
|---|---|
| Release date | 15 Apr 2026 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Proprietary (API only) [models.dev] |
| Context window | 8K (8,192 tokens) [models.dev] |
| Max output | 16K tokens [models.dev] |
| Knowledge cutoff | Jan 2025 [models.dev] |
| Input | Text [models.dev] |
| Output | Audio [models.dev] |
| Reasoning mode | Yes [models.dev] |
| Tool calling | No [models.dev] |
Gemini 3.1 Flash TTS Preview API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| Gemini API gemini-3.1-flash-tts-preview | $1 | $20 | – | 8K | models.dev, 4 Oct 2026 |
Frequently asked questions
What is the context window of Gemini 3.1 Flash TTS Preview?
Gemini 3.1 Flash TTS Preview 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 3.1 Flash TTS Preview API cost?
Through Gemini API, Gemini 3.1 Flash TTS Preview costs $1 per million input tokens and $20 per million output tokens. Prices last verified 4 Oct 2026.
Is Gemini 3.1 Flash TTS Preview open source?
No. Gemini 3.1 Flash TTS Preview is a proprietary model; Google DeepMind has not released its weights. It is available through APIs including Gemini API.
When was Gemini 3.1 Flash TTS Preview released?
Google DeepMind released Gemini 3.1 Flash TTS Preview on 15 Apr 2026, according to models.dev.
Change history
No changes detected since we started tracking this model. We re-check every source daily.