Text to Speech Leaderboard

Models ranked by ELO Rating, based on independent benchmark evaluations.

Each row shows the model's benchmark score alongside its pricing and output speed, so you can evaluate quality-to-cost tradeoffs at a glance.

All Leaderboards

Text to Speech Leaderboard

Top 101 models ranked by elo rating

Text to Image Image Editing Text to Speech Text to Video Image to Video

Rank	Model	Creator	ELO Rating	95% CI
🥇	Inworld TTS 1.5 Max Inworld	Inworld	1212	-19/19
🥈	Sonic 3.5 Cartesia	Cartesia	1218	-14/14
🥉	Gemini 3.1 Flash TTS Google	Google	1216	-13/13
4	Fun-Realtime-TTS Alibaba	Alibaba	1210	-14/14
5	Realtime TTS-2 - Research Preview Inworld	Inworld	1202	-14/14
6	xAI Text to Speech xAI	xAI	1197	-14/14
7	Inworld TTS 1.5 Mini Inworld	Inworld	1159	-16/16
8	Fun-Realtime-TTS-Preview Alibaba	Alibaba	1193	-15/15
9	Realtime TTS 1.5 Max Inworld	Inworld	1197	-14/14
10	Async Flash v1.5 async	async	1186	-15/15
11	Realtime TTS-2 - Research Preview Inworld	Inworld	1158	-14/14
12	StepAudio 2.5 TTS StepFun	StepFun	1184	-17/17
13	Luna TTS VUI Labs	VUI Labs	1181	-16/16
14	Eleven v3 ElevenLabs	ElevenLabs	1179	-12/12
15	Speech 2.8 HD MiniMax	MiniMax	1171	-12/12
16	Inworld TTS 1 Max Inworld	Inworld	1166	-13/13
17	Lightning V3.1 Pro TTS (Jun 2026) Smallest.ai	Smallest.ai	1167	-15/15
18	Async Pro v1.0 async	async	1157	-15/15
19	Speech 2.8 Turbo MiniMax	MiniMax	1152	-12/12
20	Step TTS 2 (Mar 2026) StepFun	StepFun	1150	-14/14
21	Step TTS 2 StepFun	StepFun	1105	-19/19
22	Qwen3.5 Omni Flash Alibaba	Alibaba	1105	-46/46
23	Realtime TTS 1.5 Mini Inworld	Inworld	1150	-13/13
24	Speech 2.6 Turbo MiniMax	MiniMax	1137	-12/12
25	SIMBA 3.0 Speechify	Speechify	1134	-14/14
26	Speech 2.6 HD MiniMax	MiniMax	1132	-12/12
27	Azure HD 2.5 Microsoft	Microsoft	1120	-14/14
28	Inworld TTS 1 Inworld	Inworld	1129	-12/12
29	Step Audio EditX (Mar 2026) StepFun	StepFun	1113	-14/14
30	Multilingual v2 ElevenLabs	ElevenLabs	1111	-10/10
31	Fish Audio S2 Pro Fish Audio	Fish Audio	1111	-14/14
32	Speech-02-HD MiniMax	MiniMax	1109	-12/12
33	OpenAudio S1 Mini Fish Audio	Fish Audio	1065	-15/15
34	Seed-TTS 2.0 ByteDance Seed	ByteDance Seed	1091	-14/14
35	Turbo v2.5 ElevenLabs	ElevenLabs	1108	-11/11
36	Gradium TTS Gradium	Gradium	1104	-15/15
37	TTS-1 HD OpenAI	OpenAI	1097	-12/12
38	Lightning V3.1 Pro Smallest.ai	Smallest.ai	1099	-13/13
39	Flash v2.5 ElevenLabs	ElevenLabs	1095	-11/11
40	Gradium TTS (Jun 2026) Gradium	Gradium	1095	-16/16
41	Speech-02-Turbo MiniMax	MiniMax	1089	-12/12
42	Step Audio EditX StepFun	StepFun	1061	-18/18
43	MiMo-V2.5-TTS Xiaomi	Xiaomi	1089	-14/14
44	Chatterbox HD Resemble AI	Resemble AI	1087	-13/13
45	TTS-1 OpenAI	OpenAI	1086	-11/11
46	Sonic 3 Cartesia	Cartesia	1082	-12/12
47	GPT-4o mini TTS OpenAI	OpenAI	1056	-22/22
48	Gemini 2.5 Flash Lite TTS Google	Google	1079	-12/12
49	Studio Google	Google	1076	-12/12
50	Voxtral TTS Mistral	Mistral	1075	-14/14
51	Gemini 2.5 Flash TTS Google	Google	1044	-14/14
52	Polly Generative Amazon	Amazon	1072	-12/12
53	GPT-Realtime-2 OpenAI	OpenAI	1070	-15/15
54	SIMBA 1.6 Speechify	Speechify	1068	-13/13
55	OpenAudio S1 Fish Audio	Fish Audio	1066	-11/11
56	Polly Long-Form Amazon	Amazon	1066	-14/14
57	Gemini 2.5 Pro TTS Google	Google	1036	-14/14
58	Kokoro 82M v1.0 Kokoro	Kokoro	1063	-11/11
59	T2A-01-HD MiniMax	MiniMax	1062	-11/11
60	Octave 2 Hume AI	Hume AI	1061	-12/12
61	Chirp 3: HD Google	Google	1057	-12/12
62	Async Flash v1.0 async	async	1057	-12/12
63	Journey Google	Google	1057	-13/13
64	Magpie-Multilingual 357M (Feb 2026) NVIDIA	NVIDIA	1056	-14/14
65	Maya1 Maya Research	Maya Research	1054	-12/12
66	Coda Rime	Rime	1045	-14/14
67	Sonic English (Oct 2024) Cartesia	Cartesia	1044	-12/12
68	Gemini 2.5 Pro (Dec 2025) Google	Google	1040	-13/13
69	SIMBA 1.0 Speechify	Speechify	1038	-11/11
70	Gemini 2.5 Flash TTS (Dec 2025) Google	Google	1036	-13/13
71	Azure Neural Microsoft	Microsoft	1035	-18/18
72	Lightning v3.1 Smallest.ai	Smallest.ai	1033	-13/13
73	T2A-01-Turbo MiniMax	MiniMax	1028	-11/11
74	Octave TTS Hume AI	Hume AI	1026	-11/11
75	MiMo-V2-TTS Xiaomi	Xiaomi	1015	-15/15
76	MAI-Voice-1 Microsoft	Microsoft	1014	-14/14
77	Magpie-Multilingual 357M NVIDIA	NVIDIA	1013	-12/12
78	Arcana v3 Rime	Rime	1011	-14/14
79	Fish Speech 1.5 Fish Audio	Fish Audio	1010	-11/11
80	Chatterbox Resemble AI	Resemble AI	1007	-11/11
81	Zonos-v0.1 Zyphra	Zyphra	1000	0/0
82	Murf Speech Gen 2 Murf AI	Murf AI	975	-11/11
83	LMNT LMNT	LMNT	970	-13/13
84	OpenVoice v2 OpenVoice	OpenVoice	968	-13/13
85	VibeVoice 1.5B Microsoft	Microsoft	966	-14/14
86	VibeVoice 7B Microsoft	Microsoft	965	-14/14
87	Magpie Multilingual NVIDIA	NVIDIA	940	-14/14
88	Neuphonic TTS Neuphonic	Neuphonic	940	-14/14
89	Qwen3 TTS Flash Alibaba	Alibaba	933	-14/14
90	XTTS v2 Coqui	Coqui	918	-15/15
91	Qwen3 TTS Alibaba	Alibaba	915	-13/13
92	WaveNet Google	Google	900	-12/12
93	StyleTTS 2 StyleTTS	StyleTTS	892	-15/15
94	Mist V2 Rime	Rime	889	-15/15
95	Polly Neural Amazon	Amazon	886	-14/14
96	Neural2 Google	Google	884	-12/12
97	Standard Google	Google	878	-12/12
98	Noiz TTS Noiz	Noiz	845	-17/17
99	MetaVoice v1 MetaVoice	MetaVoice	832	-18/18
100	Falcon (Beta) Murf AI	Murf AI	832	-15/15
101	Polly Standard Amazon	Amazon	818	-15/15