Report Bug / Feature Request

TTS Arena — AI Voice Model Leaderboard

Ṣàfikún àwọn móòdù àkọlé-si-ìbàlẹ̀ 20+. Àwọn ìṣàfarawe-ìgbà, àwọn ìṣàfihàn-ìjọba, àti ìṣàfihàn-ìgbà.

Ṣàfihàn

A kò ní àwọn ìrànwọ́ TTS nínú ìtàn rẹ̀. Yọ̀ọ̀kan rán wà láti fàyè gba àwọn rẹ̀! Fi Ojú Rẹ̀ pamọ́

Àwọn Àwọn Ààyè-iṣẹ́

Ṣàfihàn àyọkà, yan àwọn ìṣàmúlò-ètò mejì, àtí ṣàfihàn àwọn àwọn ìrísí-lẹ́tà. Àwọn ìṣàmúlò-ètò ìpele-ètò ọ̀fẹ̀ kò niló kọ̀ǹpútà kan.

Àwọn àwọn àwòrán

Àwọn ìṣàmúlò-ètò B

Àwọn ìṣàmúlò-ètò ọ̀fẹ̀ náà tí kò bá kọ̀ǹpútà. Ṣẹ̀dà to compare premium models.

Àwọn ìṣàmúlò-ètò

#	Àwọn ìṣàmúlò-ètò	Àwọn Àkọ́kọ́	Àwọn Àwọn Àwọn	Ìjánu-ìsún	Àwọn àwọn ààyè-iṣẹ́
1	Kokoro Lightweight 82M parameter model delivering studio-quality speech with blazing-fast inference. 82M 1200h 2024	4.8 /5	5.0 /5 1 Àwọn ìṣàmúlò-ètò	fast	Free
2	CosyVoice 2 Alibaba's scalable streaming TTS with human-parity naturalness and near-zero latency. 300M 200000h 2024	4.26 /5	Àwọn àwòrán	medium	Standard
3	Chatterbox State-of-the-art zero-shot voice cloning with emotion control from Resemble AI. 300M 2025	4.25 /5	Àwọn àwòrán	medium	Premium
4	StyleTTS 2 Human-level text-to-speech through style diffusion and adversarial training. 100M 585h 2024	4.23 /5	Àwọn àwòrán	medium	Premium
5	Piper A fast, local neural text to speech system optimized for Raspberry Pi and embedded devices. 15M 2023	4.15 /5	Àwọn àwòrán	fast	Free
6	MeloTTS High-quality multilingual text-to-speech that runs on CPU with minimal latency. 25M 2024	4.13 /5	Àwọn àwòrán	fast	Free
7	Dia TTS Multi-speaker dialog generation model that creates natural conversations between speakers. 1.6B 2024	4.09 /5	Àwọn àwòrán	medium	Standard
8	VITS Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech. 25M 585h 2021	4.0 /5	Àwọn àwòrán	fast	Free
9	Orpheus Human-level emotional TTS model trained on 100K hours of speech data. 3B 100000h 2025	4.0 /5	Àwọn àwòrán	medium	Standard
10	OpenVoice Instant voice cloning with granular control over style, emotion, and accent. 300M 2024	4.0 /5	Àwọn àwòrán	medium	Premium
11	IndexTTS-2 Zero-shot TTS with fine-grained emotion control and high expressiveness. 300M 2025	3.91 /5	Àwọn àwòrán	medium	Standard
12	Spark TTS Voice cloning TTS with controllable emotion and speaking style via prompts. 500M 2025	3.9 /5	Àwọn àwòrán	medium	Standard
13	Parler TTS Describe the voice you want in natural language and Parler generates matching speech. 880M 45000h 2024	3.83 /5	Àwọn àwòrán	medium	Standard
14	Tortoise TTS Multi-voice text-to-speech focused on quality with autoregressive architecture. 400M 50000h 2022	3.7 /5	Àwọn àwòrán	slow	Premium
15	Bark Transformer-based text-to-audio model that generates realistic speech, music, and sound effects. 350M 100000h 2023	3.57 /5	Àwọn àwòrán	slow	Standard
16	Bark Small Lighter version of Bark with faster inference and lower memory usage. 150M 100000h 2023	—	Àwọn àwòrán	medium	Standard
17	GLM-TTS Achieves the lowest character error rate among open-source TTS models. 300M 2025	—	Àwọn àwòrán	medium	Standard
18	GPT-SoVITS Few-shot voice cloning TTS that replicates any voice from just 5 seconds of audio. 200M 2024	—	Àwọn àwòrán	slow	Standard
19	Qwen3 TTS Alibaba's multilingual TTS with voice cloning, preset voices, and voice design from text. 1.7B 2025	—	Àwọn àwòrán	medium	Standard
20	Sesame CSM Conversational speech model generating natural dialogue with appropriate timing and emotion. 1B 2025	—	Àwọn àwòrán	slow	Premium
21	Chatterbox Turbo Faster Chatterbox with sub-200ms latency and paralinguistic tags for laughs, coughs, and more. 350M 2025	—	Àwọn àwòrán	fast	Standard
22	Dia 2 Streaming-first conversational TTS with multi-speaker dialogue and paralinguistic cues. 2B 2025	—	Àwọn àwòrán	fast	Standard
23	VoxCPM Tokenizer-free TTS producing 44.1kHz audio with context-aware paragraph consistency. 500M 1800000h 2025	—	Àwọn àwòrán	fast	Standard
24	OuteTTS LLM-based TTS that runs on CPU, GPU, or browser via llama.cpp and Transformers.js. 1B 5000h 2025	—	Àwọn àwòrán	fast	Free
25	TADA Zero-hallucination TTS with text-acoustic dual alignment, 5x faster than comparable LLM TTS. 1B 2026	—	Àwọn àwòrán	fast	Standard
26	VibeVoice Microsoft's multi-speaker long-form TTS generating up to 90 minutes with 4 distinct speakers. 1.5B 100000h 2025	—	Àwọn àwòrán	fast	Standard
27	Pocket TTS Lightweight 100M parameter model by Kyutai with voice cloning from a single sample. 100M 50000h 2025	—	Àwọn àwòrán	fast	Free
28	Kitten TTS Ultra-lightweight TTS under 80MB. Runs on CPU without GPU. 80M 2025	—	Àwọn àwòrán	fast	Free
29	CosyVoice3 Next-generation multilingual TTS with bi-streaming, emotion control, and zero-shot voice cloning. 500M 200000h 2025	—	Àwọn àwòrán	fast	Standard
30	MOSS-TTS Ultra-long 20-language TTS supporting up to 1 hour of continuous generation with phoneme-level control. 8B 500000h 2026	—	Àwọn àwòrán	medium	Premium
31	MegaTTS3 ByteDance's sparse alignment TTS with adjustable intelligibility vs. speaker similarity. 1B 100000h 2025	—	Àwọn àwòrán	slow	Premium

Àwọn Ààyè-iṣẹ́ Ìṣàmúlò-ètò

Oṣiṣẹ TTS.ai benchmark scores lori awọn iwọn mẹta: naturalness, accuracy, ati iyara.

Kokoro

Free

Ìṣàfilọ́lẹ̀ 4.8/5

Àwọn ìṣàfarawé 4.7/5

Ìjánu-ìsún 4.9/5

Gbogbogbo 4.8/5

CosyVoice 2

Standard

Ìṣàfilọ́lẹ̀ 4.5/5

Àwọn ìṣàfarawé 4.4/5

Ìjánu-ìsún 3.8/5

Gbogbogbo 4.26/5

Chatterbox

Premium

Ìṣàfilọ́lẹ̀ 4.7/5

Àwọn ìṣàfarawé 4.5/5

Ìjánu-ìsún 3.4/5

Gbogbogbo 4.25/5

StyleTTS 2

Premium

Ìṣàfilọ́lẹ̀ 4.5/5

Àwọn ìṣàfarawé 4.3/5

Ìjánu-ìsún 3.8/5

Gbogbogbo 4.23/5

Piper

Free

Ìṣàfilọ́lẹ̀ 3.5/5

Àwọn ìṣàfarawé 4.2/5

Ìjánu-ìsún 4.95/5

Gbogbogbo 4.15/5

MeloTTS

Free

Ìṣàfilọ́lẹ̀ 3.8/5

Àwọn ìṣàfarawé 4.1/5

Ìjánu-ìsún 4.6/5

Gbogbogbo 4.13/5

Dia TTS

Standard

Ìṣàfilọ́lẹ̀ 4.6/5

Àwọn ìṣàfarawé 4.3/5

Ìjánu-ìsún 3.2/5

Gbogbogbo 4.09/5

VITS

Free

Ìṣàfilọ́lẹ̀ 3.4/5

Àwọn ìṣàfarawé 4.0/5

Ìjánu-ìsún 4.8/5

Gbogbogbo 4.0/5

Orpheus

Standard

Ìṣàfilọ́lẹ̀ 4.3/5

Àwọn ìṣàfarawé 4.1/5

Ìjánu-ìsún 3.5/5

Gbogbogbo 4.0/5

OpenVoice

Premium

Ìṣàfilọ́lẹ̀ 4.0/5

Àwọn ìṣàfarawé 4.1/5

Ìjánu-ìsún 3.9/5

Gbogbogbo 4.0/5

IndexTTS-2

Standard

Ìṣàfilọ́lẹ̀ 4.3/5

Àwọn ìṣàfarawé 4.1/5

Ìjánu-ìsún 3.2/5

Gbogbogbo 3.91/5

Spark TTS

Standard

Ìṣàfilọ́lẹ̀ 4.2/5

Àwọn ìṣàfarawé 4.0/5

Ìjánu-ìsún 3.4/5

Gbogbogbo 3.9/5

Parler TTS

Standard

Ìṣàfilọ́lẹ̀ 4.1/5

Àwọn ìṣàfarawé 3.9/5

Ìjánu-ìsún 3.4/5

Gbogbogbo 3.83/5

Tortoise TTS

Premium

Ìṣàfilọ́lẹ̀ 4.6/5

Àwọn ìṣàfarawé 4.4/5

Ìjánu-ìsún 1.8/5

Gbogbogbo 3.7/5

Bark

Standard

Ìṣàfilọ́lẹ̀ 4.2/5

Àwọn ìṣàfarawé 3.8/5

Ìjánu-ìsún 2.5/5

Gbogbogbo 3.57/5

Àwọn Ìṣàmúlò-ètò

Àtòjọ-ẹ̀yàn Àtòjọ-ẹ̀yàn

Àwọn ààyè-iṣẹ́: 4x NVIDIA Tesla P40 (24GB VRAM kọọkan), 96GB gbogbogbo
Àwọn àyọkà ìsàlẹ̀-ilà: 5 awọn igun ti a ṣe deede ti o ni awọn aṣa ọrọ oriṣiriṣi (iṣaro, ibaraẹnisọrọ, imọ-ẹrọ, ifẹ, awọn ede pupọ)
Àwọn ìṣàmúlò-ètò Automatic metrics (MOS estimation, WER, RTF) combined with human listening tests
Àwọn ìṣàmúlò-ètò: Àwọn ìṣàmúlò-ètò kọ̀ǹpútà kọ̀ǹpútà kọ̀ǹpútà kọ̀ǹpútà kọ̀ǹpútà

Àwọn ìṣàmúlò-ètò ìṣàmúlò-ètò

Ìṣàfihàn (40%): Prosody, intonation, rhythm, emotions — bawo ni o ṣe n ṣe igbọran eniyan?
Ìṣàmúlò-ètò (30%): Pronunciation correctness, word error rate, intelligibility
Ìjánu-ìsẹ́ (30%): Fákìtì àkókó-ìgbá (sékètì àwòrán / sékètì ìṣàfilọ́lẹ̀). Kéré = rọ́ọ̀nù.
Gbogbogbo: Aṣàfilọ́lẹ̀: 0.4 x Aṣàfilọ́lẹ̀ + 0.3 x Aṣàfilọ́lẹ̀ + 0.3 x Ìjáde

Àwọn Àmì-ìwé: Àwọn ìṣàmúlò-ètò ìṣàfihàn àwọn àkọlé àwọn ìṣàmúlò-ètò wà. Àwọn ìṣàmúlò-ètò ìṣàfihàn lè yatọ láti inú àkọlé àwọn ìṣàfihàn, àwọn ìṣàfihàn ede, àti àwọn ìṣàfihàn ìgbọ̀n. Àwọn ìṣàfihàn ìjọbà náà náà náà ní àwọn ààtò ìṣàfihàn tí a dá lori àwọn ìlòòròrò tí a lò.

Àwọn Àtòjọ-ẹ̀yàn

The TTS Arena is a leaderboard that ranks AI text-to-speech models based on official benchmark tests and community ratings. Compare models side-by-side, listen to samples, and vote for the ones that sound best to you.

We run standardized tests on each model using the same text passages, hardware, and evaluation criteria. Scores cover naturalness (how human it sounds), accuracy (pronunciation and intelligibility), and speed (generation time). All tests use our GPU server with NVIDIA Tesla P40 GPUs.

Òyà! Tẹ̀ àwọn àwọn ìtà ààyè-iṣẹ́ nínú àwọn àwọn ìṣàmúlò-ètò wọn láti fi àwọn ìṣàmúlò-ètò náà hàn láti 1 sí 5. Ò ní àwọn ìṣàmúlò-ètò tí o fẹ́ láti fi àwọn ìṣàmúlò-ètò rẹ̀ pamọ́. Àwọn ìṣàmúlò-ètò rẹ̀ ń fi àwọn ìṣàmúlò-ètò àwọn ìjọbà pọ̀jú àwọn ìṣàmúlò-ètò tí a fi fihan nínú àwọn àwọn ìṣàmúlò-ètò. O lè yipada àwọn ìṣàmúlò-ètò rẹ̀ nígbà gbogbo.

Ṣàfihàn àwọn àkọlé, yan àwọn àwòrán meji, ki o si tẹ̀ Pánẹ́ẹ̀lì. Àwòrán mejila náà náà náà náà náà náà. Fẹ̀ẹ̀ wọn nínú àwọn àwòrán náà ki o si tẹ̀tẹ̀ fún ohun tí o dara ju. Àwòrán tí a fi pamọ́ yìí náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà náà

Ìṣàfilọ́lẹ̀ ìṣàfilọ́lẹ̀ ìṣàfilọ́lẹ̀ ìṣàfilọ́lẹ̀. Ìṣàfilọ́lẹ̀ ìṣàfilọ́lẹ̀ ìṣàfilọ́lẹ̀ ìṣàfilọ́lẹ̀. Ìṣàfilọ́lẹ̀ ìṣàfilọ́lẹ̀ ìṣàfilọ́lẹ̀. Ìṣàfilọ́lẹ̀ ìṣàfilọ́lẹ̀.

Àwọn ìṣàmúlò-ètò tí kò ní àwọn ààyè-ètò ìṣàmúlò-ètò ìṣàmúlò-ètò ní pàtó àwọn àwọn ìṣàmúlò-ètò tí kò ní àwọn ìṣàmúlò-ètò ìṣàmúlò-ètò. Àwọn ìṣàmúlò-ètò àwọn ìṣàmúlò-ètò ní pàtó fún àwọn ìṣàmúlò-ètò yìí.

Official benchmarks are updated when models receive significant updates or when new models are added. Community ratings update in real-time as users vote. The leaderboard data is cached for 5 minutes for performance.

Àwọn ìṣàmúlò-ètò ọ̀fẹ́ (Kokoro, Piper, VITS, MeloTTS) ní àwọn àmì-àṣírí 0. Àwọn ìṣàmúlò-ètò ìpéwọ̀n lo àwọn àmì-àṣírí 2x (gẹ́gẹ́ bíi, àwọn àmì-àṣírí 1,000 tí a fi kọ́kọ́kọ́ kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́kọ́

Fun àwọn àwọn ìṣàmúlò-ètò ìṣàmúlò-ètò, Kokoro (àwọn ìpele àìfẹ́) ǹfi ìdáràn tí o darà. Fún ìṣàmúlò-ètò ìranṣẹ́, ṣàfihàn Chatterbox tàbí CosyVoice 2. Fún àwọn àkọlé àwọn ìtàn, MeloTTS tàbí CosyVoice 2. Fún àwọn àkọlé àwọn ìṣàfihàn, Bark tàbí Dia. Ló àtòjọ-ẹ̀yàn ìtalólobò láti ṣàfihàn àwọn àkọlé àwọn àkọlé rẹ̀.

Òyà, o lè ṣẹ̀dà àti ìpàpọ̀ àwòrán láti inú àwọn àwọn ìṣàmúlò-ètò mejì fún àwọn àwọn ìṣàmúlò-ètò tí kò ní kọ́́ntà láti lò. Àwọn ìpàpọ̀ àwọn ìṣàmúlò-ètò Premium ní àwọn àwọn àmì-àṣírí.

A n wa fun igbẹkẹle nipa lilo awọn ọrọ idanwo ti a ṣe deede, awọn ohun elo kọmputa ti o jọra, ati awọn ipolongo iwadi ti o tọka si gbogbo awọn awoṣe. Awọn itẹsiwaju agbegbe n fun ifihan agbara ti o da lori ara wọn. Iṣẹ-ṣiṣe wa ni a ṣalaye ni apakan Iṣẹ-ṣiṣe Benchmark ni isalẹ.

Models are ranked primarily by official benchmark overall score, then by community average rating as a tiebreaker. Models without benchmarks are ranked below those with benchmarks, ordered by community rating.

5.0/5 (1)

Wá Àwòrán Rẹ̀

Wá àwọn móòdù fún ọ̀fẹ̀ pẹlú Kokoro, Piper, VITS, tàbí MeloTTS. Kò ní àwọn àwọn ìṣàmúlò-ètò tí a fẹ́.

Ṣàfihàn Wó Àwọn Ìtàn

TTS Arena — AI Voice Model Leaderboard

Àwọn Àwọn Ààyè-iṣẹ́

Àwọn ìṣàmúlò-ètò

Àwọn Ààyè-iṣẹ́ Ìṣàmúlò-ètò

Kokoro

CosyVoice 2

Chatterbox

StyleTTS 2

Piper

MeloTTS

Dia TTS

VITS

Orpheus

OpenVoice

IndexTTS-2

Spark TTS

Parler TTS

Tortoise TTS

Bark

Àwọn Ìṣàmúlò-ètò

Àtòjọ-ẹ̀yàn Àtòjọ-ẹ̀yàn

Àwọn ìṣàmúlò-ètò ìṣàmúlò-ètò

Àwọn Àtòjọ-ẹ̀yàn

Kini Ìgbà Ìṣàmúlò-ètò TTS?

Bawo ni a ṣe ṣe iṣiro awọn aago benchmark ọfiisi?

Mò lè fi àwọn ìṣàmúlò-ètò lọ́wọ́lọ́wọ́?

Bawo ni ìparápọ̀ àwọn ààyè-iṣẹ́ ṣe n ṣiṣẹ́?

Kini idi ti àwọn ìṣàmúlò-ètò àwọn mìíràn kò ní àwọn ìṣàmúlò-ètò ìpéwọ̀n?

Ìgbà wo nínú àwọn ìṣàfihàn àwọn ìpéwọ̀n náà tí a fi pamọ́?

Kini iyatọ laarin àwọn ìpele ọ̀fẹ̀, ìpejuwe, àti àwọn ìpele ìpele?

Àwọn àwọn àwọn àwọn àwọn àwọn

Àwọn ìṣàyẹwo ìpéwọ̀n náà jẹ́ àìdájú?

How are models ranked when scores are tied?

Wá Àwòrán Rẹ̀