whatmodel.sh · find the best text-to-speech models you can run

Text-to-speech models in the VITS 2021 LJ Speech human MOS model set

A leaderboard of the best text-to-speech models. Models are ranked by one score that combines 101 published benchmarks. Filter by your computer or budget to find the best one you can use.

1 models · scores combine 101 benchmarks · updated how it works · find a leaderboard · benchmark your machine
task[all tasks][voice cloning]
Filter by your hardware and budget
+ more · VITS 2021 LJ Speech human MOS
set[all sets][Vapi Humanness · Bradley–Terry rating, 2026-09-25 snapshot · 148][VITS 2021 LJ Speech human MOS · 5][Grad-TTS 2021 LJ Speech human MOS · 4]
score[overall][within selected set]

Filter the model list while keeping overall scores. Models without a shared score scale are not yet calibrated; select a set to see its own scores.

Detect your exact chip or graphics card:

curl -G whatmodel.sh/tts -d max=0 --data-urlencode "mac=$(sysctl -n hw.memsize machdep.cpu.brand_string)"Mac

curl -G whatmodel.sh/tts -d max=0 --data-urlencode "ram=$(awk '/MemT/{print $2}' /proc/meminfo)" --data-urlencode "nv=$(nvidia-smi --query-gpu=name,memory.total --format=csv,noheader 2>/dev/null)"Linux

curl.exe -G whatmodel.sh/tts -d max=0 --data-urlencode "ram=$((gcim Win32_ComputerSystem).TotalPhysicalMemory)" --data-urlencode "nv=$(nvidia-smi --query-gpu=name,memory.total --format=csv,noheader 2>$null)"Windows

$ terminal

detecting your OS…

Run curl "whatmodel.sh/tts?set=vits2021-ljspeech-mos"to get this list in your terminal (add &format=json for agents).

ram[8][16][24][32][48][64][96][128][192][256]GB
gpu[apple silicon][graphics card][none]
price[local][$1][$2][$5][$10][$20][$50][any]max per M chars

detecting your OS…

#modelscore↓where↓speed↓RAM↓get itsources
#modelscore↓where↓speed↓RAM↓get itsources
—VITS (LJ Speech) Kakao / KAISTnot yet calibratedlocal~0.2GBhow to run › VITS: ICML 2021 original listening studies

1 of 187 catalogue models listed here · sources and licences

Models outside this leaderboard (4 models)

No current run option verified: Tacotron 2 + HiFi-GAN (LJ Speech) · Tacotron 2 + fine-tuned HiFi-GAN (LJ Speech) · Glow-TTS + HiFi-GAN (LJ Speech) · Glow-TTS + fine-tuned HiFi-GAN (LJ Speech)

* new or thinly tested: ranked on too few benchmark results · † only the maker’s own numbers so far · ~RAM is estimated; full context may need more memory