Updated daily at 05:00 UTC
Text-to-speech
Gemini TTS
Gemini models that turn text into controllable single- or multi-speaker speech.
By Google DeepMind.
Versions
5 versions
| Model | Maker | Kind | Released | Context | Input $/1M | Output $/1M |
|---|---|---|---|---|---|---|
| Gemini 3.8 Flash TTSGemini TTS | Google DeepMind | Text-to-speech | 22 Sep 2026 | 8.2K | $0.50 | $9.00 |
| Gemini 3.8 Flash-Lite TTSGemini TTS | Google DeepMind | Text-to-speech | 22 Sep 2026 | 8.2K | $0.50 | $6.00 |
| Gemini 3.1 Flash TTSGemini TTS · Legacy | Google DeepMind | Text-to-speech | 15 Apr 2026 | 8.2K | $1.00 | $20.00 |
| Gemini 2.5 Flash TTSGemini TTS · Legacy | Google DeepMind | Text-to-speech | 20 May 2025 | 8.2K | $0.50 | $10.00 |
| Gemini 2.5 Pro TTSGemini TTS · Legacy | Google DeepMind | Text-to-speech | 20 May 2025 | 8.2K | $1.00 | $20.00 |
- Gemini 3.8 Flash TTSGoogle DeepMind · 22 Sep 2026 · 8.2K context$0.50in / 1M
- Gemini 3.8 Flash-Lite TTSGoogle DeepMind · 22 Sep 2026 · 8.2K context$0.50in / 1M
- Gemini 3.1 Flash TTSGoogle DeepMind · 15 Apr 2026 · 8.2K context$1.00in / 1M
- Gemini 2.5 Flash TTSGoogle DeepMind · 20 May 2025 · 8.2K context$0.50in / 1M
- Gemini 2.5 Pro TTSGoogle DeepMind · 20 May 2025 · 8.2K context$1.00in / 1M