Provider · read on October 27, 2026
Fish Audio text-to-speech models, ranked by speed
6 of the 96 text-to-speech (TTS) models in this index are filed under Fish Audio , led by Fish Audio Drama 3 Preview, Fish Audio S2.1 Pro and Fish Audio S2.1 Pro Free. 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 |
|---|---|---|---|---|---|---|---|---|
| 10 |  Fish Audio Drama 3 PreviewFish Audio | Fast enough | 209.3 ms | 146 ms | 1,245 | $15 | Customer service, Voice agents, Assistants, Entertainment, Knowledge sharing | |
| 25 |  Fish Audio S2.1 ProFish Audio | Visible delay | 533 ms | 328.1 ms | 1,184 | $15 | Customer service, Assistants, Entertainment, Knowledge sharing | |
| 31 |  Fish Audio S2.1 Pro FreeFish Audio | Visible delay | 1,137.9 ms | 793.8 ms | Not rated | Not collected | Not rated | |
| 49 (tie) |  Fish Audio S2 ProFish Audio | No tier | Not timed | Not timed | Not timed | 1,108 | $15 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 54 |  Fish Audio OpenAudio S1Fish Audio | No tier | Not timed | Not timed | Not timed | 1,084 | $15 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 62 (tie) |  Fish Audio OpenAudio S1 MiniFish Audio | No tier | Not timed | Not timed | Not timed | 1,043 | $15 | Knowledge sharing |
Frequently asked questions
- Which Fish Audio TTS model is the fastest?
- Fish Audio Drama 3 Preview, with a P95 time to first audio of 209.3 ms in Coval's 30-day window. Of the 6 models on this page, 3 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.