Skip to content
IFAI

Model rankings

716 models · 4 boards · 2 sources

Text-to-speech arena · Anonymous head-to-head votes · Updated October 24, 2025

Best voice
Speech-02-HDMiniMax1,134Score
Best open model
Kokoro 82M v1.0Kokoro1,065Score
Best from China
Speech-02-HDMiniMax1,134Score
Top three by Score
1Speech-02-HDMiniMax1,134
2Speech-02-TurboMiniMax1,122
3TTS-1OpenAI1,122
Top three open models
1Kokoro 82M v1.0Kokoro · #12 overall1,065
2Fish Speech 1.5Fish Audio · #21 overall1,032
3ChatterboxResemble AI · #22 overall1,027
This week's changes
Claude 4.5 Haiku (Reasoning)Intelligence · #20New
Qwen3 VL 8B InstructIntelligence · #108New
RankChangeModelScore95% interval
1—Speech-02-HDClosedMiniMax1,134—
2—Speech-02-TurboClosedMiniMax1,122—
3—TTS-1ClosedOpenAI1,122—
4—ElevenLabs v3ClosedElevenLabs1,115—
5—Multilingual v2ClosedElevenLabs1,114—
6—Turbo v2.5ClosedElevenLabs1,107—
7—Flash v2.5ClosedElevenLabs1,097—
8—Inworld TTS 1ClosedInworld1,096—
9—OpenAudio S1ClosedFish Audio1,092—
10—Polly Long-FormClosedAmazon1,067—
11—T2A-01-HDClosedMiniMax1,065—
12—Chatterbox HDClosedResemble AI1,059—
13—OpenAudio S1 MiniClosedFish Audio1,057—
14—Polly GenerativeClosedAmazon1,056—
15—GPT-4o mini TTSClosedOpenAI1,055—
16—Azure NeuralClosedMicrosoft Azure1,048—
17—TTS-1 HDClosedOpenAI1,041—
18—SimbaClosedSpeechify1,039—
19—StudioClosedGoogle1,035—
20—T2A-01-TurboClosedMiniMax1,027—
21—Sonic English (Oct '24)ClosedCartesia1,025—
22—Octave 2ClosedHume AI1,024—
23—Octave TTSClosedHume AI1,018—
24—JourneyClosedGoogle1,016—
25—Magpie MultilingualClosedNVIDIA1,012—
26—VibeVoice 1.5BClosedMicrosoft Azure991—
27—LMNTClosedLMNT976—
28—Murf Speech Gen 2ClosedMurf AI968—
29—Qwen3 TTS FlashClosedAlibaba958—
30—Polly NeuralClosedAmazon916—
31—WaveNetClosedGoogle884—
32—StandardClosedGoogle850—
33—Neural2ClosedGoogle843—
34—Polly StandardClosedAmazon813—

Intelligence over time

Each maker's best model at the time on the Artificial Analysis Intelligence Index, by the month it was released.

Gained most · Anthropic +57.2Highest now · Anthropic 64.6Gap between highest and lowest 18.1 ptsTime range Nov 2025 – Nov 2026
64.6Anthropic60.0Google56.9OpenAI50.1Meta46.5Kimi

Arena data comes from the leaderboard dataset it publishes on Hugging Face (CC BY 4.0). Only each board's overall leaderboard is used; scores and ranks are unchanged. dataset · CC BY 4.0

Artificial Analysis data comes from its API (artificialanalysis.ai). Scores are unchanged; ranks follow the scores. artificialanalysis.ai

Open or closed follows the license Arena gives; prices and Artificial Analysis intelligence show only where model names match, otherwise “—”.