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

Best text-to-speech models to run locally on a 8GB Mac

A leaderboard of the best text-to-speech models you can run locally on a Mac with 8GB of memory. OmniVoice is #1 right now, followed by Qwen3-TTS 12Hz 1.7B Base and VoxCPM2. Models are ranked by one score that combines 101 published benchmarks. Each model shows the download that fits and the command to run it.

69 models · scores combine 101 benchmarks · updated how it works · find a leaderboard · benchmark your machine
task[all tasks][voice cloning]
Models for 8GB RAM · Apple Silicon → ~5GB fast · local only · reset
+ more
chip[M1][M2][M3][M4]
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=apple&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
18OmniVoice · fp32 k2-fsa (Xiaomi)66±2local~3.3GBhow to run › OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models (arXiv:2604.00688v3)Building and Evaluating Fixed-Voice Thai TTS from Synthetic Speech (Wayu Research / Paxa Labs / Typhoon; arXiv:2609.03502v1)nineninesix/gepard-1.0 model card (Seed-TTS-eval benchmark table)Higgs Audio v3 comparison tables in SGLang-Omni cookbook (Boson AI contribution)nsanku TTS Benchmark (GhanaNLP community Space)Arabic TTS Arena (Navid AI) · leaderboard snapshot 2026-09-24
25Qwen3-TTS 12Hz 1.7B Base · bf16 (qwen-tts) Alibaba (Qwen)65±1local~4.5GBhow to run › UltraEval-Audio (OpenBMB) · TTS replication resultsRaon-OpenTTS: Open Models and Data for Robust Text-to-Speech (arXiv:2605.20830v2)Qwen-Audio-3.0-TTS technical reportZONOS2 Technical Report (ZTTS1-Eval results)Higgs Audio v3 comparison tables in SGLang-Omni cookbook (Boson AI contribution)Qwen/Qwen3-TTS-12Hz-1.7B-Base model card+3
27VoxCPM2 · bf16 (voxcpm) OpenBMB64±1local~5GBhow to run › UltraEval-Audio (OpenBMB) · TTS replication resultsQwen-Audio-3.0-TTS technical reportZONOS2 Technical Report (ZTTS1-Eval results)nineninesix/gepard-1.0 model card (Seed-TTS-eval benchmark table)ZTTS1-Eval results snapshot (Zyphra)Arabic TTS Arena (Navid AI) · leaderboard snapshot 2026-09-24
29Wayu-Paxa-TTS-Edge · fp32 (wayu-tts package) Wayu Research / Paxa Labs64±4†local~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~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~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~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~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)
49CosyVoice2-0.5B · fp32 (CosyVoice repo) Alibaba (FunAudioLLM)61±1local~4.1GBhow to run › UltraEval-Audio (OpenBMB) · TTS replication resultsRaon-OpenTTS: Open Models and Data for Robust Text-to-Speech (arXiv:2605.20830v2)VoxCPM: Tokenizer-Free TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning (arXiv:2509.24650v1)DMOSpeech 2: Reinforcement Learning for Duration Prediction in Metric-Optimized Speech Synthesis (arXiv:2507.14988v1)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)+1
50E2 TTS Base (F5-TTS reproduction) · fp32 SWivid (SJTU X-LANCE)60±2local~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~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)
63ZONOS2 8B · q4_k (zonos2.cpp) Zyphra57±2†local~5.2GBhow to run › ZONOS2 Technical Report (ZTTS1-Eval results)ZTTS1-Eval results snapshot (Zyphra)
64Supertonic 3 · onnx-fp32 (supertonic Python SDK 1.3.x) Supertone55±10*local~0.4GBhow to run › Arabic TTS Arena (Navid AI) · leaderboard snapshot 2026-09-24
68CosyVoice-300M · fp32 (CosyVoice repo) Alibaba (FunAudioLLM)54±3local~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
69Chatterbox Multilingual V3 · fp32 (chatterbox) Resemble AI54±10*local~3.2GBhow to run › Arabic TTS Arena (Navid AI) · leaderboard snapshot 2026-09-24
73Kokoro 82M v1.0 · bf16 hexgrad52±3local~0.7GBhow 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~1.5GBhow to run › LEMAS multilingual audio suite report
76Spark-TTS 0.5B · fp32 (Spark-TTS repo CLI) SparkAudio52±3local~3.9GBhow to run › DMOSpeech 2: Reinforcement Learning for Duration Prediction in Metric-Optimized Speech Synthesis (arXiv:2507.14988v1)RVCBench: Benchmarking Robustness of Voice Cloning Across Modern Audio Generation Models (arXiv:2602.00443v2)
79OpenVoice V1 · fp32 (myshell-ai/OpenVoice) MyShell51±14*local~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~1.4GBhow to run › LEMAS multilingual audio suite report
85MMS TTS Amharic · fp32 (transformers VitsModel) Meta50±16*local~0.2GBhow to run › Addis AI Amharic TTS benchmark
86Chatterbox · fp32 (chatterbox-tts 0.1.7) Resemble AI50±5local~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~2.6GBhow to run › TTSDS v1 published results
89SILMA TTS v1 · fp32 checkpoint (silma-tts 1.0.5) SILMA AI48±10*local~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~2.4GBhow to run › EmergentTTS-Eval six-category leaderboardEmergentTTS-Eval v1 paper (arXiv:2505.23009v1) · Table 1 automatic MOS
93Kyutai TTS 1.6B en/fr · bf16 (moshi-mlx) Kyutai47±5*local~4.1GBhow to run › EmergentTTS-Eval six-category leaderboard
96Piper (en_US lessac medium) · onnx-fp32 (piper-tts 1.8.0) Open Home Foundation (Piper)47±5*local~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~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~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)
104Parler-TTS Mini v1 · fp32 (parler-tts) Hugging Face (Parler-TTS)44±6*local~3.5GBhow to run › VERSA toolkit paper: TTS demonstration (arXiv:2412.17667v2)
106Nabra-82M v0.1 · fp32 (Kokoro KModel, Oddadmix/kokoro fork) oddadmix42±10*local~0.3GBhow to run › Arabic TTS Arena (Navid AI) · leaderboard snapshot 2026-09-24
107OpenAudio S1 Mini · bf16 (fish-speech official repo CLI) Fish Audio41±5local~3.6GBhow to run › LEMAS multilingual audio suite reportArabic TTS Arena (Navid AI) · leaderboard snapshot 2026-09-24CodecMOS-Accent: listening-test MOS of zero-shot TTS across English accents (arXiv:2603.14328v1)
108Fish Speech 1.5 · bf16 (fish-speech repo) Fish Audio41±3local~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~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~0.7GBhow to run › carun/tts-bench: intelligibility benchmark of four open TTS engines (published run, 2026-09-10)
114Zonos v0.1 · bf16 Zyphra39±4local~4.3GBhow to run › EmergentTTS-Eval six-category leaderboardbalacoon speech_gen_baselines · zero-shot TTS metrics (VCTK, DAPS-celeb)EmergentTTS-Eval v1 paper (arXiv:2505.23009v1) · Table 1 automatic MOS
121Amphion VALL-E v2 recipe (MLS) · fp32 (Amphion repo) Amphion (CUHK-Shenzhen)36±3local~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
122NeuTTS Air · bf16 (neutts 1.4.1) Neuphonic36±10*local~5GBhow to run › CodecMOS-Accent: listening-test MOS of zero-shot TTS across English accents (arXiv:2603.14328v1)
126VoiceCraft 830M (giga830M) · fp32 (VoiceCraft repo) Puyuan Peng et al. (UT Austin)32±4†local~4.5GBhow to run › VoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wild (arXiv:2403.16973v3)
127VALL-E X (Plachtaa open implementation) · fp32 (Plachtaa/VALL-E-X repo) Plachtaa (community)31±4local~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~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~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~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
132Tortoise TTS v2 · fp32 (coqui-tts 0.27.5) Tortoise29±2local~4.5GBhow to run › TTSDS2 listening test results (ttsds/listening_test)ZS-TTS-Evaluation (Edresson Casanova) · zero-shot TTS metrics of XTTS, YourTTS, TorToiSe and StyleTTS 2EmergentTTS-Eval six-category leaderboardAn Evaluation Framework for TTS Voice Reconstruction (SAP dysarthric speakers; arXiv:2606.21343v1)EmergentTTS-Eval v1 paper (arXiv:2505.23009v1) · Table 1 automatic MOSCodecMOS-Accent: listening-test MOS of zero-shot TTS across English accents (arXiv:2603.14328v1)+2
137Piper (tr_TR dfki medium) · onnx-fp32 (piper-tts) Open Home Foundation (Piper)26±4*local~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~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
139Bark · fp32 (transformers) Suno25±3local~4.5GBhow to run › TTSDS2 listening test results (ttsds/listening_test)EmergentTTS-Eval six-category leaderboardEmergentTTS-Eval v1 paper (arXiv:2505.23009v1) · Table 1 automatic MOSTTSDS2 multilingual benchmark results (ttsds/leaderboard_data)TTSDS v1 published results
140SpeechT5 TTS · fp32 (transformers) Microsoft23±3local~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~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~0.2GBhow to run › Antalia-2 Mini model card (cloud0day3/antalia-mini), public Freya-TR-Eval re-run table
147Glow-TTS Common Voice (Turkish) · fp32 · CPU Coqui TTS / Fatih Akademi11±4*local~4GBhow to run › Antalia-2 Mini model card (cloud0day3/antalia-mini), public Freya-TR-Eval re-run table
—Breeze TTS 2 · mlx-mxfp8 (mlx-audio 0.5.7) BreezeBlueno reviewed resultslocal~4.6GBhow to run ›
—Chatterbox Turbo · fp32 (chatterbox-tts 0.1.7) Resemble AIno reviewed resultslocal~3GBhow to run ›
—FastPitch (Coqui LJ Speech) · fp32 · CPU Coqui TTS / Eren Gölge @erogolno reviewed resultslocal~4GBhow to run ›
—FastSpeech 2 + HiFi-GAN (SpeechBrain LJ Speech) · fp32 · CPU SpeechBrainno reviewed resultslocal~4GBhow to run ›
—Glow-TTS (Coqui LJ Speech) · fp32 · CPU Coqui TTS / Eren Gölge @erogolno reviewed resultslocal~4GBhow to run ›
—Glow-TTS Mai (Ukrainian) · fp32 · CPU Coqui TTS / @robinhadno reviewed resultslocal~4GBhow to run ›
—Kitten TTS Mini 0.8 · fp32 (mlx-audio) KittenMLno reviewed resultslocal~0.3GBhow to run ›
—KittenTTS 2 · ternary-packed LM (kittenml 0.9.3) KittenMLno reviewed resultslocal~2.1GBhow to run ›
—LightSpeech + Parallel WaveGAN · fp32 · CPU (microsoft/NeuralSpeech LightSpeech repo, LJSpeech test set) Microsoft NeuralSpeechno reviewed resultslocal~0GBhow to run ›
—Neural HMM TTS (Coqui LJ Speech) · fp32 · CPU Coqui TTS / Shivam Metha @shivammehta25no reviewed resultslocal~4GBhow to run ›
—OverFlow (Coqui LJ Speech) · fp32 · CPU Coqui TTS / Eren Gölge @erogolno reviewed resultslocal~4GBhow to run ›
—Pocket TTS (English) · fp32 (pocket-tts 3.3.0) Kyutaino reviewed resultslocal~0.2GBhow to run ›
—SpeedySpeech (Coqui LJ Speech) · fp32 · CPU Coqui TTS / Eren Gölge @erogolno reviewed resultslocal~4GBhow to run ›
—Tacotron 2 DDC (Coqui LJ Speech) · fp32 · CPU Coqui TTS / Eren Gölge @erogolno reviewed resultslocal~4GBhow to run ›
—VITS Common Voice (Portuguese) · fp32 · CPU Coqui TTS / @NeonGeckoComno reviewed resultslocal~4GBhow to run ›
—VITS CSS10 (French) · fp32 · CPU Coqui TTS / @NeonGeckoComno reviewed resultslocal~4GBhow to run ›
—VITS CSS10 (Spanish) · fp32 · CPU Coqui TTS / @NeonGeckoComno reviewed resultslocal~4GBhow to run ›
—VITS Thorsten (German) · fp32 · CPU Coqui TTS / @thorstenMuellerno reviewed resultslocal~4GBhow to run ›

+ 118 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