Provider · read on October 27, 2026
Google text-to-speech models, ranked by speed
7 of the 96 text-to-speech (TTS) models in this index are filed under Google , led by Google Chirp 3: HD, Google Gemini 3.8 Flash TTS and Google Gemini 3.8 Flash-Lite TTS. Same order and same measures as the full ranking.
| Rank | Model | Speed tier | P95 | Speed (shorter is faster) | Median | Listener Elo | Price per 1M chars | Best for |
|---|---|---|---|---|---|---|---|---|
| 29 |  Google Chirp 3: HDGoogle | Visible delay | 917.2 ms | 534.1 ms | 1,061 | $30 | Customer service, Assistants, Entertainment, Knowledge sharing | |
| 33 |  Google Gemini 3.8 Flash TTSGoogle | No tier | Not timed | Not timed | Not timed | 1,280 | $15 to $16.5 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 34 (tie) |  Google Gemini 3.8 Flash-Lite TTSGoogle | No tier | Not timed | Not timed | Not timed | 1,256 | $10 to $11 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 37 (tie) |  Google Gemini 3.1 Flash TTSGoogle | No tier | Not timed | Not timed | Not timed | 1,212 | $18.3 to $33.3 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 52 (tie) |  Google Gemini 2.5 Flash Lite TTSGoogle | No tier | Not timed | Not timed | Not timed | 1,087 | $9.2 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 57 (tie) |  Google Gemini 2.5 Flash TTS (Dec 2025)Google | No tier | Not timed | Not timed | Not timed | 1,067 | $9.2 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 64 (tie) |  Google Gemini 2.5 Pro (Dec 2025)Google | No tier | Not timed | Not timed | Not timed | 1,040 | $18.3 | Customer service, Assistants, Entertainment, Knowledge sharing |
Frequently asked questions
- Which Google TTS model is the fastest?
- Google Chirp 3: HD, with a P95 time to first audio of 917.2 ms in Coval's 30-day window. Of the 7 models on this page, 1 are timed.
- How are these models ordered?
- As in the full ranking: speed tier, then P95 time to first audio, with ties within 10 ms ordered by median time to first audio. Models Coval does not time follow, ordered by listener Elo; models with neither measure come last, in alphabetical order.