ElevenLabsMiniMaxAudio matchupSpeech output
Eleven v3vs.MiniMax Speech 2.8
Which model is better?
Eleven v3 does better in independent tests.
Pick Eleven v3 for
Pick MiniMax Speech 2.8 for
Shared tests
Independent evaluators and leaderboards only, the newest shared snapshot per evaluator. With 95 % ranges a lead counts when they do not overlap; for hit rates, when it holds in a 95 % test. Without any uncertainty figure at most “slightly ahead”.
VoiceArena
Eleven v3 aheadEleven v3 is clearly ahead in 5 of 5 subtests, MiniMax Speech 2.8 in none.
VoiceArena TTS Elo: Mexican Spanish
95 % ranges 991 to 1,023 and 769 to 817, as of October 28, 2026
VoiceArena TTS Elo: Brazilian Portuguese
95 % ranges 1,025 to 1,043 and 841 to 861, as of October 28, 2026
VoiceArena TTS Elo: Vietnamese
95 % ranges 1,023 to 1,043 and 899 to 919, as of October 28, 2026
Show all 5 subtests
| Subtest | Eleven v3 | MiniMax Speech 2.8 | Verdict |
|---|---|---|---|
| VoiceArena TTS Elo: Mexican Spanish | 1,007 | 793 | Eleven v3 ahead |
| VoiceArena TTS Elo: Brazilian Portuguese | 1,034 | 851 | Eleven v3 ahead |
| VoiceArena TTS Elo: Vietnamese | 1,033 | 909 | Eleven v3 ahead |
| VoiceArena TTS Elo: Arabic MSA | 1,007 | 906 | Eleven v3 ahead |
| VoiceArena TTS Elo: Hindi | 1,044 | 941 | Eleven v3 ahead |
Source · latest October 28, 2026
Artificial Analysis
Eleven v3 aheadEleven v3 is clearly ahead in 1 of 2 subtests, MiniMax Speech 2.8 in none. 1 is level.
Artificial Analysis Controlled Voice Arena Elo
95 % ranges 1,063 to 1,085 and 1,012 to 1,036, as of November 3, 2026
Artificial Analysis Provider Voice Arena preference
95 % ranges 1,177 to 1,197 and 1,163 to 1,183, as of November 3, 2026
Source · latest November 3, 2026
All data side by side
Prices are verbatim from the provider, because audio models bill per minute, character or token.
| Eleven v3 | MiniMax Speech 2.8 | |
|---|---|---|
| Task | Speech output | Speech output |
| Developer | ElevenLabs | MiniMax |
| Status | Active | Active |
| Released | n/a | January 23, 2026 |
| Weights | proprietary | proprietary |
| Runs locally | no | no |
| Price | n/a | speech-2.8-hd costs $100 per 1M characters, synchronous and asynchronous |
| Popularity (out of 100) | 39 | 0 |