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

Best voice cloning models to run locally

A leaderboard of the best voice cloning models you can run on your own computer. dots.tts SOAR 2B is #1 right now, followed by LongCat-AudioDiT-3.5B and dots.tts MF 2B (MeanFlow, NFE 4). Models are ranked on how clear the cloned voice is and how much it sounds like the original speaker. Each model shows the download that fits and the command to run it.

36 models · scores combine 13 benchmarks · updated how it works · find a leaderboard · benchmark your machine
task[all tasks][voice cloning]

Scores use reviewed voice cloning evaluations only. Compare scores within this task. Models without task measurements are excluded.

Filter by your hardware and budget · local only · reset
+ more
set[all sets][Seed-TTS test-en · Whisper large-v3 WER · 43][MiniMax TTS · 9-language speaker similarity · 3]

Filter the model list while keeping task 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?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][$20][$50][any]max per M chars

detecting your OS…

Score vs memory to run

#modeltask score↓where↓speed↓RAM↓get itsources
#modeltask score↓where↓speed↓RAM↓get itsources
2dots.tts SOAR 2B dots.tts67±4local~5.2GBhow to run › Qwen-Audio-3.0-TTS technical reportdots.tts Technical Report
4LongCat-AudioDiT-3.5B Meituan66±4local~15GBhow to run › Qwen-Audio-3.0-TTS technical reportmeituan-longcat/LongCat-AudioDiT-3.5B model card (Seed benchmark table)
6dots.tts MF 2B (MeanFlow, NFE 4) dots.tts62±6†local~5.2GBhow to run › dots.tts Technical Report
7FireRedTTS3 (base) FireRedTeam (Xiaohongshu)62±4local~12GBhow to run › UltraEval-Audio (OpenBMB) · TTS replication results
8VoxCPM2 OpenBMB61±3local~2.3GBhow to run › UltraEval-Audio (OpenBMB) · TTS replication resultsQwen-Audio-3.0-TTS technical reportnineninesix/gepard-1.0 model card (Seed-TTS-eval benchmark table)
9LongCat-AudioDiT-1B Meituan60±6†local~5.7GBhow to run › meituan-longcat/LongCat-AudioDiT-3.5B model card (Seed benchmark table)
10Higgs Audio V3 TTS Boson AI59±6*†local~10GBhow to run › Higgs Audio v3 comparison tables in SGLang-Omni cookbook (Boson AI contribution)
11OmniVoice k2-fsa (Xiaomi)59±3local~3.3GBhow to run › Higgs Audio v3 comparison tables in SGLang-Omni cookbook (Boson AI contribution)OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models (arXiv:2604.00688v3)nineninesix/gepard-1.0 model card (Seed-TTS-eval benchmark table)nsanku TTS Benchmark (GhanaNLP community Space)
13Qwen3-TTS 12Hz 1.7B Base Alibaba (Qwen)58±3local~4.5GBhow to run › UltraEval-Audio (OpenBMB) · TTS replication resultsHiggs Audio v3 comparison tables in SGLang-Omni cookbook (Boson AI contribution)Raon-OpenTTS: Open Models and Data for Robust Text-to-Speech (arXiv:2605.20830v2)Qwen/Qwen3-TTS-12Hz-1.7B-Base model card
14IndexTTS (v1) IndexTeam (bilibili)57±7local~1.2GBhow to run › DiSTAR: Diffusion over a Scalable Token Autoregressive Representation for Speech Generation (arXiv:2510.12210v2)
15VoxCPM 0.5B OpenBMB57±4local~5GBhow to run › UltraEval-Audio (OpenBMB) · TTS replication resultsRaon-OpenTTS: Open Models and Data for Robust Text-to-Speech (arXiv:2605.20830v2)
16F5-TTS v1 Base SWivid (SJTU X-LANCE)56±6local~1.4GBhow to run › DiSTAR: Diffusion over a Scalable Token Autoregressive Representation for Speech Generation (arXiv:2510.12210v2)
17Fish Audio S2 Pro Fish Audio56±3local~11GBhow to run › UltraEval-Audio (OpenBMB) · TTS replication resultsHiggs Audio v3 comparison tables in SGLang-Omni cookbook (Boson AI contribution)nineninesix/gepard-1.0 model card (Seed-TTS-eval benchmark table)Fish Audio S2 Technical Report
18Qwen3-TTS 12Hz 0.6B Base Alibaba (Qwen)56±4local~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)
19IndexTTS-2 IndexTeam (bilibili)54±3local~8.9GBhow to run › UltraEval-Audio (OpenBMB) · TTS replication resultsHiggs Audio v3 comparison tables in SGLang-Omni cookbook (Boson AI contribution)Raon-OpenTTS: Open Models and Data for Robust Text-to-Speech (arXiv:2605.20830v2)OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models (arXiv:2604.00688v3)
20ZipVoice k2-fsa (Xiaomi)54±6local~0.2GBhow to run › OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models (arXiv:2604.00688v3)
21DMOSpeech 2 Columbia University / NewsBreak (Yinghao Aaron Li, Xilin Jiang et al.)53±6†local~4.3GBhow to run › DMOSpeech 2: Reinforcement Learning for Duration Prediction in Metric-Optimized Speech Synthesis (arXiv:2507.14988v1)
22Fun-CosyVoice3-0.5B-2512 Alibaba (FunAudioLLM)53±3local~5.4GBhow to run › UltraEval-Audio (OpenBMB) · TTS replication resultsRaon-OpenTTS: Open Models and Data for Robust Text-to-Speech (arXiv:2605.20830v2)
23E2 TTS Base (F5-TTS reproduction) SWivid (SJTU X-LANCE)53±4local~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)
26MOSS-TTS v1.5 (8B) OpenMOSS53±3local~24GBhow to run › UltraEval-Audio (OpenBMB) · TTS replication resultsHiggs Audio v3 comparison tables in SGLang-Omni cookbook (Boson AI contribution)SGLang-Omni serving cookbooks (SGLang-Omni team measurements)
28F5-TTS Base (v0) SWivid (SJTU X-LANCE)52±6†local~1.4GBhow to run › F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching (arXiv:2410.06885v1)
29GLM-TTS Z.ai52±4local~8.9GBhow to run › UltraEval-Audio (OpenBMB) · TTS replication results
30Higgs Audio V2 Boson AI51±6*†local~7GBhow to run › Higgs Audio v3 comparison tables in SGLang-Omni cookbook (Boson AI contribution)
32MaskGCT Amphion (CUHK-Shenzhen)50±3local~6.6GBhow to run › Raon-OpenTTS: Open Models and Data for Robust Text-to-Speech (arXiv:2605.20830v2)OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models (arXiv:2604.00688v3)DMOSpeech 2: Reinforcement Learning for Duration Prediction in Metric-Optimized Speech Synthesis (arXiv:2507.14988v1)Amphion MaskGCT README · zero-shot TTS results table
33CosyVoice2-0.5B Alibaba (FunAudioLLM)48±3local~4.1GBhow to run › UltraEval-Audio (OpenBMB) · TTS replication resultsRaon-OpenTTS: Open Models and Data for Robust Text-to-Speech (arXiv:2605.20830v2)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)
35Spark-TTS 0.5B SparkAudio41±5local~2.9GBhow to run › DMOSpeech 2: Reinforcement Learning for Duration Prediction in Metric-Optimized Speech Synthesis (arXiv:2507.14988v1)
36CosyVoice-300M Alibaba (FunAudioLLM)40±5local~2.3GBhow to run › F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching (arXiv:2410.06885v1)Amphion MaskGCT README · zero-shot TTS results table
37Llasa-8B HKUST Audio37±4local~20GBhow to run › DMOSpeech 2: Reinforcement Learning for Duration Prediction in Metric-Optimized Speech Synthesis (arXiv:2507.14988v1)Raon-OpenTTS: Open Models and Data for Robust Text-to-Speech (arXiv:2605.20830v2)
38FireRedTTS (v1) FireRedTeam (Xiaohongshu)33±5local~3.1GBhow to run › F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching (arXiv:2410.06885v1)DiSTAR: Diffusion over a Scalable Token Autoregressive Representation for Speech Generation (arXiv:2510.12210v2)
39VoiceCraft 830M TTSEnhanced Puyuan Peng et al. (UT Austin)28±12*local~4.5GBhow to run › Amphion MaskGCT README · zero-shot TTS results table
40XTTS v2 Coqui23±6local~1.9GBhow to run › ZS-TTS-Evaluation (Edresson Casanova) · zero-shot TTS metrics of XTTS, YourTTS, TorToiSe and StyleTTS 2Amphion MaskGCT README · zero-shot TTS results table
41StyleTTS 2 (LibriTTS) Yinghao Aaron Li et al. (Columbia University)17±7*local~0.9GBhow to run › ZS-TTS-Evaluation (Edresson Casanova) · zero-shot TTS metrics of XTTS, YourTTS, TorToiSe and StyleTTS 2
42Tortoise TTS v2 Tortoise12±7*local~4.5GBhow to run › ZS-TTS-Evaluation (Edresson Casanova) · zero-shot TTS metrics of XTTS, YourTTS, TorToiSe and StyleTTS 2
43YourTTS Coqui / Edresson Casanova et al.-1±7*†local~0.4GBhow to run › ZS-TTS-Evaluation (Edresson Casanova) · zero-shot TTS metrics of XTTS, YourTTS, TorToiSe and StyleTTS 2
—Voxtral TTS (4B) Mistralnot yet calibratedlocal~10GBhow to run › Voxtral TTS
—ZONOS2 8B Zyphranot scored yetlocal~5.2GBhow to run ›

+ 11 more don't fit your machine or budget · show them

47 of 47 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