ElevenLabs
eleven_v3_conversational
Measured 2026-07-03
Run eleven_v3_conversational on Speko →One API, every model on this board.
Naturalness
1590
Win % · 95% CI
66%
60–72%
Drift
20
Synth p50
266ms
265–268 two-sweep p50
Robustness
0.30
Fined:
• fatal · currency — dropped the minus sign (7 of 7 transcripts)
→ we sent “A refund of -$0.99 was applied.”
→ it said “A refund of 99 cents was applied.”
• fatal · large numbers — never said “three point four million” (37 of 43 transcripts)
→ we sent “The clip hit 3.4M views and 1.2k shares.”
→ it said “The clip hit three point four M views and one point two k shares.”
• fatal · math operators — never said “greater than or equal to” (47 of 49 transcripts)
→ we sent “Keep x ≥ 10 at all times.”
→ it said “Keep X ten at all times.”
+ 11 more fined
Cost / 1M chars
$50.0
v3 Conversational is its own $0.05/1k product on elevenlabs.io/pricing/api, half the plain v3 rate. The FAQ on that same page collapses the two at $0.10/1k; the itemized card and the per-plan table both say $0.05, so they win.
Share this result
Embed the live badge
[](https://benchmarks.speko.ai/tts/elevenlabs-eleven-v3-conversational)
<a href="https://benchmarks.speko.ai/tts/elevenlabs-eleven-v3-conversational"><img src="https://benchmarks.speko.ai/badge/tts/elevenlabs-eleven-v3-conversational.svg" alt="Speko tts rank"></a>
https://benchmarks.speko.ai/tts/elevenlabs-eleven-v3-conversational