ElevenLabs · read on October 27, 2026
ElevenLabs Eleven v4
ElevenLabs Eleven v4 is a TTS (text-to-speech) model from ElevenLabs. No benchmark in this index times it over 30 days, so it has no speed tier. It ranks 32 of 86 in the full ranking.
- Speed tier
- No tier
- P95 / median
- Not timed / Not timed
- Listener Elo
- 1,333
- Price per 1M chars
- $80
Where it ranks
Full ranking: 32 of 86. Use case ranks, by speed:
The tier and the ranks are computed by this site from the benchmarks' figures, not declared by ElevenLabs.
Measurements and sources
Speko
| Naturalness score | 1,708 |
| Latency, board chart | 852 ms |
| Latency, model page sweep (median) | 844 ms |
| Numbers and dates pronunciation | 0.9 |
Artificial Analysis
| Listener Elo | 1,333 |
| Listener Elo, 95% interval | 16 |
| Listener Elo, customer service | 1,374 |
| Hard passages pronounced correctly | 91.7% |
Cekura
| Time to first audio, streamed text | 561 ms |
| Time to first audio, text sent whole | 678 ms |
| Reading accuracy | 80.4% |
| Estimated naturalness (1 to 5) | 4.42 |
Details
| Provider | ElevenLabs |
| Access | Proprietary |
| Streaming | A benchmark measures its time to first audio |
| Languages tested | Spanish, German, French, Portuguese, Japanese, Chinese, Arabic, Hindi, Vietnamese |
| Measured by | Artificial Analysis, Cekura, Speko |
| Official site | elevenlabs.io |
Not collected
Nothing below is estimated. Each line says which measure is missing and why.
- Speed (Coval median time to first audio): not measured by Coval (reading of 2026-10-27, 30-day window)
- Speed (Coval P95 time to first audio): not measured by Coval (reading of 2026-10-27, 30-day window)
Sources
- https://artificialanalysis.ai/text-to-speech (read on October 27, 2026)
- https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice (read on October 27, 2026)
- https://benchmarks.cekura.ai/text-to-speech (read on October 27, 2026)
- https://benchmarks.speko.ai/tts/ (read on October 27, 2026)
Values are copied from these pages on the date shown. The match between this model and its benchmark entries is inferred, because a source writes the name differently: Cekura: “ElevenLabs v4”. See the methodology.
Compare it with the reference model: Gradium TTS vs ElevenLabs Eleven v4.