TTS Arena. AI Voice Model Leaderboard
Vergelijk 20+ text-to-speech modellen. Officiële benchmarks, communautaire ratings en side-by-side vergelijking.
Vergelijking van zij-bij-zij
Typ tekst, kies twee modellen, en vergelijk de resultaten. Free-tier modellen vereisen geen account.
Gratis modellen werken zonder account. Aanmelden om premiummodellen te vergelijken.
Model Leaderboard
| # | Model | Ambtenaar | Gemeenschap | Uw beoordeling | Snelheid | Niveau |
|---|---|---|---|---|---|---|
| 1 |
Kokoro
Lightweight 82M parameter model delivering studio-quality speech with blazing-fast inference.
82M
1200h
2024
|
4.8 /5 |
5.0
/5
1 stemmen
|
fast | Free | |
| 2 |
CosyVoice 2
Alibaba's scalable streaming TTS with human-parity naturalness and near-zero latency.
300M
200000h
2024
|
4.26 /5 | Nog geen stemmen | medium | Standard | |
| 3 |
Chatterbox
State-of-the-art zero-shot voice cloning with emotion control from Resemble AI.
300M
2025
|
4.25 /5 | Nog geen stemmen | medium | Premium | |
| 4 |
StyleTTS 2
Human-level text-to-speech through style diffusion and adversarial training.
100M
585h
2024
|
4.23 /5 | Nog geen stemmen | medium | Premium | |
| 5 |
Piper
A fast, local neural text to speech system optimized for Raspberry Pi and embedded devices.
15M
2023
|
4.15 /5 | Nog geen stemmen | fast | Free | |
| 6 |
MeloTTS
High-quality multilingual text-to-speech that runs on CPU with minimal latency.
25M
2024
|
4.13 /5 | Nog geen stemmen | fast | Free | |
| 7 |
Dia TTS
Multi-speaker dialog generation model that creates natural conversations between speakers.
1.6B
2024
|
4.09 /5 | Nog geen stemmen | medium | Standard | |
| 8 |
VITS
Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech.
25M
585h
2021
|
4.0 /5 | Nog geen stemmen | fast | Free | |
| 9 |
Orpheus
Human-level emotional TTS model trained on 100K hours of speech data.
3B
100000h
2025
|
4.0 /5 | Nog geen stemmen | medium | Standard | |
| 10 |
OpenVoice
Instant voice cloning with granular control over style, emotion, and accent.
300M
2024
|
4.0 /5 | Nog geen stemmen | medium | Premium | |
| 11 |
IndexTTS-2
Zero-shot TTS with fine-grained emotion control and high expressiveness.
300M
2025
|
3.91 /5 | Nog geen stemmen | medium | Standard | |
| 12 |
Spark TTS
Voice cloning TTS with controllable emotion and speaking style via prompts.
500M
2025
|
3.9 /5 | Nog geen stemmen | medium | Standard | |
| 13 |
Parler TTS
Describe the voice you want in natural language and Parler generates matching speech.
880M
45000h
2024
|
3.83 /5 | Nog geen stemmen | medium | Standard | |
| 14 |
Tortoise TTS
Multi-voice text-to-speech focused on quality with autoregressive architecture.
400M
50000h
2022
|
3.7 /5 | Nog geen stemmen | slow | Premium | |
| 15 |
Bark
Transformer-based text-to-audio model that generates realistic speech, music, and sound effects.
350M
100000h
2023
|
3.57 /5 | Nog geen stemmen | slow | Standard | |
| 16 |
Bark Small
Lighter version of Bark with faster inference and lower memory usage.
150M
100000h
2023
|
— | Nog geen stemmen | medium | Standard | |
| 17 |
Indic Parler TTS
High-quality speech for 8+ Indian languages with natural-language voice control.
900M
8000h
2024
|
— | Nog geen stemmen | slow | Standard | |
| 18 |
KhanomTan TTS
Thai-first text-to-speech with a choice of speaker voices.
85M
100h
2023
|
— | Nog geen stemmen | fast | Standard | |
| 19 |
GPT-SoVITS
Few-shot voice cloning TTS that replicates any voice from just 5 seconds of audio.
200M
2024
|
— | Nog geen stemmen | slow | Standard | |
| 20 |
Qwen3 TTS
Alibaba's multilingual TTS with preset voices and voice design from text.
1.7B
2025
|
— | Nog geen stemmen | medium | Standard | |
| 21 |
VieNeu-TTS-v2
Vietnamese + English code-switching TTS with 7 preset voices and zero-shot voice cloning. CPU-only, no GPU required.
0.3B
10000h
2026
|
— | Nog geen stemmen | fast | Standard | |
| 22 |
Sesame CSM
Conversational speech model generating natural dialogue with appropriate timing and emotion.
1B
2025
|
— | Nog geen stemmen | slow | Premium | |
| 23 |
Chatterbox Turbo
Faster Chatterbox with sub-200ms latency and paralinguistic tags for laughs, coughs, and more.
350M
2025
|
— | Nog geen stemmen | fast | Standard | |
| 24 |
VoxCPM
Tokenizer-free TTS producing 44.1kHz audio with context-aware paragraph consistency.
500M
1800000h
2025
|
— | Nog geen stemmen | fast | Standard | |
| 25 |
Kani TTS 2
Ultra-lightweight 400M English TTS model running in just 3GB VRAM.
400M
10000h
2026
|
— | Nog geen stemmen | fast | Free | |
| 26 |
OuteTTS
LLM-based TTS that runs on CPU, GPU, or browser via llama.cpp and Transformers.js.
1B
5000h
2025
|
— | Nog geen stemmen | slow | Free | |
| 27 |
VibeVoice
Microsoft's multi-speaker long-form TTS generating up to 90 minutes with 4 distinct speakers.
1.5B
100000h
2025
|
— | Nog geen stemmen | fast | Standard | |
| 28 |
Pocket TTS
Lightweight 100M parameter model by Kyutai with voice cloning from a single sample.
100M
50000h
2025
|
— | Nog geen stemmen | fast | Free | |
| 29 |
Kitten TTS
Ultra-lightweight TTS under 80MB. Runs on CPU without GPU.
80M
2025
|
— | Nog geen stemmen | fast | Free | |
| 30 |
CosyVoice3
Next-generation multilingual TTS with bi-streaming, emotion control, and zero-shot voice cloning.
500M
200000h
2025
|
— | Nog geen stemmen | fast | Standard | |
| 31 |
NAMAA Saudi TTS
First open Saudi-Arabic TTS. Native Saudi dialect with Chatterbox-quality voice cloning.
300M
2026
|
— | Nog geen stemmen | medium | Standard | |
| 32 |
Darwin TTS
Cross-modal Qwen3-TTS variant with FFN weights blended from the Qwen3-1.7B language model for sharper multilingual cloning.
2.1B
2026
|
— | Nog geen stemmen | medium | Standard | |
| 33 |
MOSS-TTSD
Multi-speaker dialogue continuation model — generate podcast-style conversations with up to 5 speakers and 60 minutes of coherent audio.
7B
2026
|
— | Nog geen stemmen | medium | Standard | |
| 34 |
Ming-Omni TTS
Compact 0.5B omni-modal speech model from inclusionAI with high-fidelity 44.1kHz output and zero-shot voice cloning.
500M
2026
|
— | Nog geen stemmen | medium | Free | |
| 35 |
MOSS-TTS Nano
Tiny 100M MOSS-TTS variant — same architecture, 80x smaller, free-tier latency.
100M
500000h
2026
|
— | Nog geen stemmen | fast | Free |
Gedetailleerde benchmarkscores
Officiële TTS.ai benchmark scoort in drie dimensies: natuurlijkheid, nauwkeurigheid en snelheid.
Kokoro
Free
CosyVoice 2
Standard
Chatterbox
Premium
StyleTTS 2
Premium
Piper
Free
MeloTTS
Free
Dia TTS
Standard
VITS
Free
Orpheus
Standard
OpenVoice
Premium
IndexTTS-2
Standard
Spark TTS
Standard
Parler TTS
Standard
Tortoise TTS
Premium
Bark
Standard
Benchmark Methodologie
Testopstelling
- Hardware: 4x NVIDIA Tesla P40 (elk 24GB VRAM), 96GB totaal
- Testtekst: 5 gestandaardiseerde passages over verschillende spraakpatronen (verhalen, dialoog, technisch, emotioneel, meertalig)
- Evaluatie: Geautomatiseerde metrics (MOS estimation, WER, RTF) gecombineerd met menselijke luistertesten
- Runs: Elk model getest 10 keer per passage, scores gemiddeld
Scorecriteria
- Natuurlijkheid (40%): Prosody, intonatie, ritme, emotie Hoe menselijk klinkt het?
- Nauwkeurigheid (30%): Uitspraak correctheid, woord foutenpercentage, begrijpelijkheid
- Snelheid (30%): Real-time factor (audio seconden / generatie seconden). Hoger = sneller.
- Algemeen: Gewogen gemiddelde: 0,4 x Natuurlijkheid + 0,3 x Nauwkeurigheid + 0,3 x Snelheid
Opmerking: Benchmarks weerspiegelen de prestaties op onze specifieke hardware en testteksten. Real-world kwaliteit kan variëren op basis van input tekst, taal en spraakselectie. Community ratings bieden een aanvullend signaal op basis van diverse werkelijke gebruik.
Veelgestelde vragen
Wat kunnen we verbeteren? Uw feedback helpt ons problemen op te lossen.
Zoek uw perfecte stem
Probeer elk model gratis met Kokoro, Piper, VITS, of MeloTTS. Geen account nodig.