Skip to content
IFAI

Model rankings

761 models · 5 boards · 2 sources

Text-to-speech arena · Anonymous head-to-head votes · Updated November 5, 2025

Best voice
Speech-02-HDMiniMax1,133Score
Best open model
Kokoro 82M v1.0Kokoro1,064Score
Best from China
Speech-02-HDMiniMax1,133Score
Top three by Score
1Speech-02-HDMiniMax1,133
2Speech-02-TurboMiniMax1,123
3TTS-1OpenAI1,120
Top three open models
1Kokoro 82M v1.0Kokoro · #11 overall1,064
2Maya1Maya Research · #21 overall1,044
3Fish Speech 1.5Fish Audio · #27 overall1,033
This week's changes
Kimi K2 ThinkingIntelligence · #3New
GPT-5Image · #5New
Wan 2.5 PreviewImage · #7New
Vivago 2.1Image · #8New
GPT Image 1 (high)Image · #15New
RankChangeModelScore95% interval
1—Speech-02-HDClosedMiniMax1,133—
2—Speech-02-TurboClosedMiniMax1,123—
3—TTS-1ClosedOpenAI1,120—
4—Multilingual v2ClosedElevenLabs1,116—
5—ElevenLabs v3ClosedElevenLabs1,115—
6—Turbo v2.5ClosedElevenLabs1,109—
7—Inworld TTS 1ClosedInworld1,100—
8—Flash v2.5ClosedElevenLabs1,099—
9—OpenAudio S1ClosedFish Audio1,091—
10—T2A-01-HDClosedMiniMax1,065—
11—Chatterbox HDClosedResemble AI1,062—
12—Polly Long-FormClosedAmazon1,062—
13—Polly GenerativeClosedAmazon1,061—
14—OpenAudio S1 MiniClosedFish Audio1,056—
15—TTS-1 HDClosedOpenAI1,055—
16—GPT-4o mini TTSClosedOpenAI1,053—
17—Magpie MultilingualClosedNVIDIA1,050—
18—Azure NeuralClosedMicrosoft Azure1,048—
19—Chirp 3: HDClosedGoogle1,045—
20—Octave 2ClosedHume AI1,041—
21—Sonic 3ClosedCartesia1,041—
22—SimbaClosedSpeechify1,038—
23—StudioClosedGoogle1,035—
24—Sonic English (Oct '24)ClosedCartesia1,034—
25—T2A-01-TurboClosedMiniMax1,030—
26—Octave TTSClosedHume AI1,019—
27—JourneyClosedGoogle1,018—
28—VibeVoice 1.5BClosedMicrosoft Azure995—
29—LMNTClosedLMNT980—
30—Murf Speech Gen 2ClosedMurf AI973—
31—Qwen3 TTS FlashClosedAlibaba960—
32—Polly NeuralClosedAmazon918—
33—WaveNetClosedGoogle887—
34—StandardClosedGoogle853—
35—Neural2ClosedGoogle846—
36—Polly StandardClosedAmazon819—

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 “—”.