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

Best text-to-speech models to run locally on a 8GB PC without a graphics card

A leaderboard of the best text-to-speech models you can run locally on a computer with 8GB of RAM and no graphics card. Wayu-Paxa-TTS-Edge is #1 right now, followed by IndexTTS (v1) and F5-TTS v1 Base. Models are ranked by one score that combines 101 published benchmarks. Each model shows the download that fits and the command to run it.

40 models · scores combine 101 benchmarks · updated how it works · find a leaderboard · benchmark your machine
task[all tasks][voice cloning]
Models for 8GB RAM · no GPU → ~3GB for models (CPU, slow) · local only · reset
+ more
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]

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?ram=8&gpu=none&max=0"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…

Score vs memory to run

#modelscore↓where↓speed↓RAM↓get itsources
#modelscore↓where↓speed↓RAM↓get itsources
29Wayu-Paxa-TTS-Edge · fp32 (wayu-tts package) Wayu Research / Paxa Labs64±4†local (slow)~0.3GBhow to run › Building and Evaluating Fixed-Voice Thai TTS from Synthetic Speech (Wayu Research / Paxa Labs / Typhoon; arXiv:2609.03502v1)
39IndexTTS (v1) · fp32 on CPU (index-tts repo CLI `indextts`) IndexTeam (bilibili)62±3local (slow)~1.2GBhow to run › DiSTAR: Diffusion over a Scalable Token Autoregressive Representation for Speech Generation (arXiv:2510.12210v2)
40F5-TTS v1 Base · fp32 SWivid (SJTU X-LANCE)62±3local (slow)~1.4GBhow to run › DiSTAR: Diffusion over a Scalable Token Autoregressive Representation for Speech Generation (arXiv:2510.12210v2)RVCBench: Benchmarking Robustness of Voice Cloning Across Modern Audio Generation Models (arXiv:2602.00443v2)
42ZipVoice · fp32 (ZipVoice repo) k2-fsa (Xiaomi)62±3local (slow)~0.6GBhow to run › OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models (arXiv:2604.00688v3)RVCBench: Benchmarking Robustness of Voice Cloning Across Modern Audio Generation Models (arXiv:2602.00443v2)
44Qwen3-TTS 12Hz 0.6B Base · bf16 (qwen-tts) Alibaba (Qwen)62±2local (slow)~2.5GBhow to run › UltraEval-Audio (OpenBMB) · TTS replication resultsQwen/Qwen3-TTS-12Hz-1.7B-Base model cardSGLang-Omni serving cookbooks (SGLang-Omni team measurements)
50E2 TTS Base (F5-TTS reproduction) · fp32 SWivid (SJTU X-LANCE)60±2local (slow)~1.3GBhow to run › DiSTAR: Diffusion over a Scalable Token Autoregressive Representation for Speech Generation (arXiv:2510.12210v2)F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching (arXiv:2410.06885v1)TTSDS2 listening test results (ttsds/listening_test)An Evaluation Framework for TTS Voice Reconstruction (SAP dysarthric speakers; arXiv:2606.21343v1)TTSDS2 multilingual benchmark results (ttsds/leaderboard_data)
60F5-TTS Base (v0) · fp32 SWivid (SJTU X-LANCE)57±2local (slow)~1.4GBhow to run › F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching (arXiv:2410.06885v1)TTSDS2 listening test results (ttsds/listening_test)TTSDS2 multilingual benchmark results (ttsds/leaderboard_data)
64Supertonic 3 · onnx-fp32 (supertonic Python SDK 1.3.x) Supertone55±10*local (slow)~0.4GBhow to run › Arabic TTS Arena (Navid AI) · leaderboard snapshot 2026-09-24
68CosyVoice-300M · fp32 (CosyVoice repo) Alibaba (FunAudioLLM)54±3local (slow)~2.3GBhow to run › F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching (arXiv:2410.06885v1)VERSA toolkit paper: TTS demonstration (arXiv:2412.17667v2)Amphion MaskGCT README · zero-shot TTS results table
73Kokoro 82M v1.0 · fp32 (kokoro package 0.9.4) hexgrad52±3local (slow)~0.3GBhow to run › EmergentTTS-Eval six-category leaderboardParadee: Distilling Kokoro-82M into an 8M-Parameter Single-Voice TTS Model (arXiv:2610.06817v1), Table 3 small-model comparisoncarun/tts-bench: intelligibility benchmark of four open TTS engines (published run, 2026-09-10)RW-Voice-EQ Bench (Hume AI)
74LEMAS-TTS (w/ prosody, multilingual_prosody) · official checkpoint (LEMAS-TTS repo, F5-TTS-based) LEMAS Project52±6*†local (slow)~1.5GBhow to run › LEMAS multilingual audio suite report
79OpenVoice V1 · fp32 (myshell-ai/OpenVoice) MyShell51±14*local (slow)~0.3GBhow to run › TTSDS v1 published results
84LEMAS-TTS (w/o prosody, multilingual_grl) · official checkpoint (LEMAS-TTS repo, F5-TTS-based) LEMAS Project50±6*†local (slow)~1.4GBhow to run › LEMAS multilingual audio suite report
85MMS TTS Amharic · fp32 (transformers VitsModel) Meta50±16*local (slow)~0.2GBhow to run › Addis AI Amharic TTS benchmark
86Chatterbox · fp32 (chatterbox-tts 0.1.7) Resemble AI50±5local (slow)~3.2GBhow to run › EmergentTTS-Eval six-category leaderboardCodecMOS-Accent: listening-test MOS of zero-shot TTS across English accents (arXiv:2603.14328v1)
87Parler-TTS Mini v0.1 · fp32 Hugging Face (Parler-TTS)49±14*local (slow)~2.6GBhow to run › TTSDS v1 published results
89SILMA TTS v1 · fp32 checkpoint (silma-tts 1.0.5) SILMA AI48±10*local (slow)~2.7GBhow to run › Arabic TTS Arena (Navid AI) · leaderboard snapshot 2026-09-24
92Orpheus TTS 3B 0.1 (finetune-prod) · gguf Q4_K_M (orpheus-cpp 0.0.3) Canopy Labs47±5local (slow)~2.4GBhow to run › EmergentTTS-Eval six-category leaderboardEmergentTTS-Eval v1 paper (arXiv:2505.23009v1) · Table 1 automatic MOS
96Piper (en_US lessac medium) · onnx-fp32 (piper-tts 1.8.0) Open Home Foundation (Piper)47±5*local (slow)~0.1GBhow to run › Paradee: Distilling Kokoro-82M into an 8M-Parameter Single-Voice TTS Model (arXiv:2610.06817v1), Table 3 small-model comparison
102GPT-SoVITS v2 · fp32 (repo api_v2.py) RVC-Boss44±4local (slow)~1.1GBhow to run › TTSDS2 listening test results (ttsds/listening_test)TTSDS2 multilingual benchmark results (ttsds/leaderboard_data)
103MeloTTS English · fp32 (MeloTTS repo CLI) MyShell44±5local (slow)~0.7GBhow to run › VERSA toolkit paper: TTS demonstration (arXiv:2412.17667v2)Audio Deepfake Detection in the Age of Advanced Text-to-Speech models (arXiv:2601.20510v1)
106Nabra-82M v0.1 · fp32 (Kokoro KModel, Oddadmix/kokoro fork) oddadmix42±10*local (slow)~0.3GBhow to run › Arabic TTS Arena (Navid AI) · leaderboard snapshot 2026-09-24
108Fish Speech 1.5 · bf16 (fish-speech repo) Fish Audio41±3local (slow)~1.5GBhow to run › TTSDS2 listening test results (ttsds/listening_test)TTSDS2 multilingual benchmark results (ttsds/leaderboard_data)
109EMA Lightning · fp32 (PyTorch) EMA Lightning (canberkkkkkk)40±3*local (slow)~0GBhow to run › Antalia-2 Mini model card (cloud0day3/antalia-mini), public Freya-TR-Eval re-run tableEMA Lightning model card (canberkkkkkk/ema-lightning), Benchmarks: Freya-TR-Eval
113Magpie TTS Multilingual 357M · f16-gguf (NVIDIA NeMo-Speech.cpp) NVIDIA39±6*local (slow)~0.7GBhow to run › carun/tts-bench: intelligibility benchmark of four open TTS engines (published run, 2026-09-10)
121Amphion VALL-E v2 recipe (MLS) · fp32 (Amphion repo) Amphion (CUHK-Shenzhen)36±3local (slow)~2.9GBhow to run › TTSDS2 listening test results (ttsds/listening_test)VERSA toolkit paper: TTS demonstration (arXiv:2412.17667v2)TTSDS2 multilingual benchmark results (ttsds/leaderboard_data)TTSDS v1 published results
127VALL-E X (Plachtaa open implementation) · fp32 (Plachtaa/VALL-E-X repo) Plachtaa (community)31±4local (slow)~1.6GBhow to run › VERSA toolkit paper: TTS demonstration (arXiv:2412.17667v2)ClonEval · Open Voice Cloning Leaderboard (AMU)CodecMOS-Accent: listening-test MOS of zero-shot TTS across English accents (arXiv:2603.14328v1)
128OuteTTS 0.2 500M · fp32 (outetts 0.3.3) OuteAI31±6*local (slow)~1.4GBhow to run › ClonEval · Open Voice Cloning Leaderboard (AMU)
130StyleTTS 2 (LibriTTS) · fp32 (styletts2 PyPI package 0.1.6) Yinghao Aaron Li et al. (Columbia University)30±2local (slow)~0.9GBhow to run › TTSDS2 listening test results (ttsds/listening_test)ZS-TTS-Evaluation (Edresson Casanova) · zero-shot TTS metrics of XTTS, YourTTS, TorToiSe and StyleTTS 2StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion (arXiv:2409.10058v1)DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factors (arXiv:2406.11427v2)An Evaluation Framework for TTS Voice Reconstruction (SAP dysarthric speakers; arXiv:2606.21343v1)RVCBench: Benchmarking Robustness of Voice Cloning Across Modern Audio Generation Models (arXiv:2602.00443v2)+2
131XTTS v2 · fp32 (coqui-tts 0.27.5) Coqui30±2local (slow)~1.9GBhow to run › Antalia-2 Mini model card (cloud0day3/antalia-mini), public Freya-TR-Eval re-run tableVoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wild (arXiv:2403.16973v3)ZS-TTS-Evaluation (Edresson Casanova) · zero-shot TTS metrics of XTTS, YourTTS, TorToiSe and StyleTTS 2StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion (arXiv:2409.10058v1)DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factors (arXiv:2406.11427v2)ClonEval · Open Voice Cloning Leaderboard (AMU)+7
137Piper (tr_TR dfki medium) · onnx-fp32 (piper-tts) Open Home Foundation (Piper)26±4*local (slow)~0.1GBhow to run › Antalia-2 Mini model card (cloud0day3/antalia-mini), public Freya-TR-Eval re-run table
138OpenVoice V2 · fp32 (myshell-ai/OpenVoice) MyShell26±3local (slow)~0.8GBhow to run › TTSDS2 listening test results (ttsds/listening_test)TTSDS2 multilingual benchmark results (ttsds/leaderboard_data)RVCBench: Benchmarking Robustness of Voice Cloning Across Modern Audio Generation Models (arXiv:2602.00443v2)TTSDS v1 published results
140SpeechT5 TTS · fp32 (transformers) Microsoft23±3local (slow)~0.7GBhow to run › TTSDS2 listening test results (ttsds/listening_test)TTSDS2 multilingual benchmark results (ttsds/leaderboard_data)
143YourTTS · fp32 (coqui-tts) Coqui / Edresson Casanova et al.18±3local (slow)~0.4GBhow to run › VoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wild (arXiv:2403.16973v3)ZS-TTS-Evaluation (Edresson Casanova) · zero-shot TTS metrics of XTTS, YourTTS, TorToiSe and StyleTTS 2DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factors (arXiv:2406.11427v2)
144MMS TTS Turkish · fp32 (transformers VitsModel) Meta18±4*local (slow)~0.2GBhow to run › Antalia-2 Mini model card (cloud0day3/antalia-mini), public Freya-TR-Eval re-run table
—Chatterbox Turbo · fp32 (chatterbox-tts 0.1.7) Resemble AIno reviewed resultslocal (slow)~3GBhow to run ›
—Kitten TTS Mini 0.8 · onnx (kittenml 0.9.3) KittenMLno reviewed resultslocal (slow)~0.1GBhow to run ›
—KittenTTS 2 · ternary-packed LM (kittenml 0.9.3) KittenMLno reviewed resultslocal (slow)~2.1GBhow to run ›
—LightSpeech + Parallel WaveGAN · fp32 · CPU (microsoft/NeuralSpeech LightSpeech repo, LJSpeech test set) Microsoft NeuralSpeechno reviewed resultslocal (slow)~0GBhow to run ›
—Pocket TTS (English) · fp32 (pocket-tts 3.3.0) Kyutaino reviewed resultslocal (slow)~0.2GBhow to run ›

+ 147 more don't fit your machine or budget · show them

187 of 187 catalogue models listed here · sources and licences

* 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