TTS Arena — AI Voice Model Leaderboard
Usporedi 20+ tekst-na-speech modele. Službeni mjerila, općenito gledanost, i usporedba uz sebe.
Još nemamo TTS glasove na vašem jeziku. Pomozite nam dodati svoje!
Prodaj svoj glas
Usporedba s drugim stranama
Tip tekst, odaberite dva modela, i usporedite rezultate. Besplatni-tier modeli ne zahtijevaju račun.
Besplatni modeli rade bez računa. Upišite se Usporediti premium modele.
Uzorak Leaderboarda
| # | Uzorak | Službeno | Zajednica | Vaša ocjena | Brzina | Nivo |
|---|---|---|---|---|---|---|
| 1 |
Kokoro
Lightweight 82M parameter model delivering studio-quality speech with blazing-fast inference.
82M
1200h
2024
|
4.8 /5 |
5.0
/5
1 glasanje
|
fast | Free | |
| 2 |
CosyVoice 2
Alibaba's scalable streaming TTS with human-parity naturalness and near-zero latency.
300M
200000h
2024
|
4.26 /5 | Još nema glasova. | medium | Standard | |
| 3 |
Chatterbox
State-of-the-art zero-shot voice cloning with emotion control from Resemble AI.
300M
2025
|
4.25 /5 | Još nema glasova. | medium | Premium | |
| 4 |
StyleTTS 2
Human-level text-to-speech through style diffusion and adversarial training.
100M
585h
2024
|
4.23 /5 | Još nema glasova. | medium | Premium | |
| 5 |
Piper
A fast, local neural text to speech system optimized for Raspberry Pi and embedded devices.
15M
2023
|
4.15 /5 | Još nema glasova. | fast | Free | |
| 6 |
MeloTTS
High-quality multilingual text-to-speech that runs on CPU with minimal latency.
25M
2024
|
4.13 /5 | Još nema glasova. | fast | Free | |
| 7 |
Dia TTS
Multi-speaker dialog generation model that creates natural conversations between speakers.
1.6B
2024
|
4.09 /5 | Još nema glasova. | medium | Standard | |
| 8 |
VITS
Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech.
25M
585h
2021
|
4.0 /5 | Još nema glasova. | fast | Free | |
| 9 |
Orpheus
Human-level emotional TTS model trained on 100K hours of speech data.
3B
100000h
2025
|
4.0 /5 | Još nema glasova. | medium | Standard | |
| 10 |
OpenVoice
Instant voice cloning with granular control over style, emotion, and accent.
300M
2024
|
4.0 /5 | Još nema glasova. | medium | Premium | |
| 11 |
IndexTTS-2
Zero-shot TTS with fine-grained emotion control and high expressiveness.
300M
2025
|
3.91 /5 | Još nema glasova. | medium | Standard | |
| 12 |
Spark TTS
Voice cloning TTS with controllable emotion and speaking style via prompts.
500M
2025
|
3.9 /5 | Još nema glasova. | medium | Standard | |
| 13 |
Parler TTS
Describe the voice you want in natural language and Parler generates matching speech.
880M
45000h
2024
|
3.83 /5 | Još nema glasova. | medium | Standard | |
| 14 |
Tortoise TTS
Multi-voice text-to-speech focused on quality with autoregressive architecture.
400M
50000h
2022
|
3.7 /5 | Još nema glasova. | slow | Premium | |
| 15 |
Bark
Transformer-based text-to-audio model that generates realistic speech, music, and sound effects.
350M
100000h
2023
|
3.57 /5 | Još nema glasova. | slow | Standard | |
| 16 |
Bark Small
Lighter version of Bark with faster inference and lower memory usage.
150M
100000h
2023
|
— | Još nema glasova. | medium | Standard | |
| 17 |
GLM-TTS
Achieves the lowest character error rate among open-source TTS models.
300M
2025
|
— | Još nema glasova. | medium | Standard | |
| 18 |
GPT-SoVITS
Few-shot voice cloning TTS that replicates any voice from just 5 seconds of audio.
200M
2024
|
— | Još nema glasova. | slow | Standard | |
| 19 |
Qwen3 TTS
Alibaba's multilingual TTS with voice cloning, preset voices, and voice design from text.
1.7B
2025
|
— | Još nema glasova. | medium | Standard | |
| 20 |
Sesame CSM
Conversational speech model generating natural dialogue with appropriate timing and emotion.
1B
2025
|
— | Još nema glasova. | slow | Premium | |
| 21 |
Chatterbox Turbo
Faster Chatterbox with sub-200ms latency and paralinguistic tags for laughs, coughs, and more.
350M
2025
|
— | Još nema glasova. | fast | Standard | |
| 22 |
Zonos
Emotion-controllable TTS with fine-grained sliders for happiness, anger, sadness, and more.
1.6B
200000h
2025
|
— | Još nema glasova. | medium | Standard | |
| 23 |
Dia 2
Streaming-first conversational TTS with multi-speaker dialogue and paralinguistic cues.
2B
2025
|
— | Još nema glasova. | fast | Standard | |
| 24 |
VoxCPM
Tokenizer-free TTS producing 44.1kHz audio with context-aware paragraph consistency.
500M
1800000h
2025
|
— | Još nema glasova. | fast | Standard | |
| 25 |
OuteTTS
LLM-based TTS that runs on CPU, GPU, or browser via llama.cpp and Transformers.js.
1B
5000h
2025
|
— | Još nema glasova. | fast | Free | |
| 26 |
TADA
Zero-hallucination TTS with text-acoustic dual alignment, 5x faster than comparable LLM TTS.
1B
2026
|
— | Još nema glasova. | fast | Standard | |
| 27 |
VibeVoice
Microsoft's multi-speaker long-form TTS generating up to 90 minutes with 4 distinct speakers.
1.5B
100000h
2025
|
— | Još nema glasova. | fast | Standard | |
| 28 |
Pocket TTS
Lightweight 100M parameter model by Kyutai with voice cloning from a single sample.
100M
50000h
2025
|
— | Još nema glasova. | fast | Free | |
| 29 |
Kitten TTS
Ultra-lightweight TTS under 80MB. Runs on CPU without GPU.
80M
2025
|
— | Još nema glasova. | fast | Free | |
| 30 |
CosyVoice3
Next-generation multilingual TTS with bi-streaming, emotion control, and zero-shot voice cloning.
500M
200000h
2025
|
— | Još nema glasova. | fast | Standard | |
| 31 |
MOSS-TTS
Ultra-long 20-language TTS supporting up to 1 hour of continuous generation with phoneme-level control.
8B
500000h
2026
|
— | Još nema glasova. | medium | Premium | |
| 32 |
MegaTTS3
ByteDance's sparse alignment TTS with adjustable intelligibility vs. speaker similarity.
1B
100000h
2025
|
— | Još nema glasova. | slow | Premium |
Detaljni referenčni rezultati
Službeni TTS.ai referentni rezultati u tri dimenzije: prirodnost, preciznost i brzina.
Kokoro
Free
Prirodnost
4.8/5
Preciznost
4.7/5
Brzina
4.9/5
Ukupno
4.8/5
CosyVoice 2
Standard
Prirodnost
4.5/5
Preciznost
4.4/5
Brzina
3.8/5
Ukupno
4.26/5
Chatterbox
Premium
Prirodnost
4.7/5
Preciznost
4.5/5
Brzina
3.4/5
Ukupno
4.25/5
StyleTTS 2
Premium
Prirodnost
4.5/5
Preciznost
4.3/5
Brzina
3.8/5
Ukupno
4.23/5
Piper
Free
Prirodnost
3.5/5
Preciznost
4.2/5
Brzina
4.95/5
Ukupno
4.15/5
MeloTTS
Free
Prirodnost
3.8/5
Preciznost
4.1/5
Brzina
4.6/5
Ukupno
4.13/5
Dia TTS
Standard
Prirodnost
4.6/5
Preciznost
4.3/5
Brzina
3.2/5
Ukupno
4.09/5
VITS
Free
Prirodnost
3.4/5
Preciznost
4.0/5
Brzina
4.8/5
Ukupno
4.0/5
Orpheus
Standard
Prirodnost
4.3/5
Preciznost
4.1/5
Brzina
3.5/5
Ukupno
4.0/5
OpenVoice
Premium
Prirodnost
4.0/5
Preciznost
4.1/5
Brzina
3.9/5
Ukupno
4.0/5
IndexTTS-2
Standard
Prirodnost
4.3/5
Preciznost
4.1/5
Brzina
3.2/5
Ukupno
3.91/5
Spark TTS
Standard
Prirodnost
4.2/5
Preciznost
4.0/5
Brzina
3.4/5
Ukupno
3.9/5
Parler TTS
Standard
Prirodnost
4.1/5
Preciznost
3.9/5
Brzina
3.4/5
Ukupno
3.83/5
Tortoise TTS
Premium
Prirodnost
4.6/5
Preciznost
4.4/5
Brzina
1.8/5
Ukupno
3.7/5
Bark
Standard
Prirodnost
4.2/5
Preciznost
3.8/5
Brzina
2.5/5
Ukupno
3.57/5
Referenčna metodologija
Postavke testa
- Hardver: 4x NVIDIA Tesla P40 (24GB VRAM svaki), ukupno 96GB
- Probni tekst: 5 standardiziranih odlomaka koji obuhvaćaju različite uzorke govora (priopćenje, dijalog, tehnički, emocionalni, višejezični)
- Procjena: Automatska metrika (ocjena MOS-a, WER, RTF-a) u kombinaciji s ljudskim testovima slušanja
- Pokreće: Svaki model testiran 10 puta po prolazu, rezultati u prosjeku
Kriteriji ocjenjivanja
- Prirodnost (40%): Prozodija, intonacija, ritam, emocije — kako to zvuči?
- Preciznost (30%): Ispravnost izgovora, stopa pogreške riječi, inteligencija
- Brzina (30%): Faktor u realnom vremenu (audio sekundi/generacija sekundi). Više = brže.
- Ukupno: Težak prosjek: 0,4 x Prirodnost + 0,3 x Preciznost + 0,3 x Brzina
Napomena: Real-world kvaliteta može varirati na temelju ulaznog teksta, jezika i glasovnog odabira. Rejtingi zajednica pružaju komplementarni signal na temelju različitih realnih upotreba.
Česta pitanja
Što možemo poboljšati? Vaša povratna informacija nam pomaže riješiti probleme.
Pronađite svoj savršeni glas
Pokušajte bilo koji model besplatno s Kokoro, Piper, VITS, ili Melotts. Nije potreban račun.