Provider · read on October 27, 2026
ElevenLabs text-to-speech models, ranked by speed
9 of the 96 text-to-speech (TTS) models in this index are filed under ElevenLabs , led by ElevenLabs Eleven v4 Turbo, ElevenLabs Flash v2.5 and ElevenLabs Eleven v4. 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 |
|---|---|---|---|---|---|---|---|---|
| 11 |  ElevenLabs Eleven v4 TurboElevenLabs | Fast enough | 238.6 ms | 188.9 ms | 1,333 | $40 | Customer service, Voice agents, Assistants, Entertainment, Knowledge sharing | |
| 12 |  ElevenLabs Flash v2.5ElevenLabs | Fast enough | 255.1 ms | 191 ms | 1,076 | $40 to $50 | Customer service, Voice agents, Assistants, Entertainment, Knowledge sharing | |
| 32 (tie) |  ElevenLabs Eleven v4ElevenLabs | No tier | Not timed | Not timed | Not timed | 1,333 | $80 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 37 (tie) |  ElevenLabs Eleven v3 ConversationalElevenLabs | No tier | Not timed | Not timed | Not timed | 1,213 | $50 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 42 (tie) |  ElevenLabs Eleven v3ElevenLabs | No tier | Not timed | Not timed | Not timed | 1,184 | $100 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 52 (tie) |  ElevenLabs Multilingual v2ElevenLabs | No tier | Not timed | Not timed | Not timed | 1,093 | $100 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 52 (tie) |  ElevenLabs Turbo v2.5ElevenLabs | No tier | Not timed | Not timed | Not timed | 1,093 | $50 | Customer service, Assistants, Entertainment, Knowledge sharing |
| Unranked |  ElevenLabs Flash v2ElevenLabs | No tier | Not timed | Not timed | Not timed | Not rated | $50 | Not rated |
| Unranked |  ElevenLabs Turbo v2ElevenLabs | No tier | Not timed | Not timed | Not timed | Not rated | $50 | Not rated |
Frequently asked questions
- Which ElevenLabs TTS model is the fastest?
- ElevenLabs Eleven v4 Turbo, with a P95 time to first audio of 238.6 ms in Coval's 30-day window. Of the 9 models on this page, 2 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.