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

Text-to-speech models in the Grad-TTS 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 2026-10-11 02:20 UTChow it works · find a leaderboard · benchmark your machine

task[all tasks][voice cloning]

Filter by your hardware and budget

+ more · Grad-TTS 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

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…

#	model	score↓	where↓	speed↓	RAM↓	get it	sources

#	model	score↓	where↓	speed↓	RAM↓	get it	sources
—	Grad-TTS + HiFi-GAN (10 steps) Grad-TTS authors / Huawei Noah	not yet calibrated	local		~0.1GB	how to run ›

1 of 187 catalogue models listed here · sources and licences

Models outside this leaderboard (3 models)

No current run option verified: FastSpeech + HiFi-GAN (xcmyz, Grad-TTS study) · Glow-TTS + HiFi-GAN (Grad-TTS study) · Tacotron2 + HiFi-GAN (Grad-TTS study)

* 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