Best voice cloning models for a 32GB Mac
A leaderboard of the best voice cloning models for a Mac with 32GB of memory. The best one that runs on it right now is LongCat-AudioDiT-3.5B, followed by VoxCPM2 and LongCat-AudioDiT-1B. Models are ranked on how clear the cloned voice is and how much it sounds like the original speaker. Models that run on it show the download that fits and the command to run it.
Scores use reviewed voice cloning evaluations only. Compare scores within this task. Models without task measurements are excluded.
+ more
$ terminal
↗ share
detecting your OS…
Score vs API price
● open weights ◆ API only ─┘ best score for the price · x: USD per 1M characters (log)
| # | model | task score↓ | where↓ | speed↓ | sources |
|---|
| # | model | task score↓ | where↓ | speed↓ | sources |
|---|---|---|---|---|---|
| 1 |  Qwen-Audio-3.0-TTS-Plus | 72±5*† | api $20.00/M chars |  | |
| 3 |  OpenAudio S1 | 67±10*† | api $15.00/M chars | | |
| 4 |  LongCat-AudioDiT-3.5B · fp32 weights (official LongCat-AudioDiT repo, transformers>=5.3) | 66±4 | local |  | |
| 8 |  VoxCPM2 · bf16 (voxcpm) | 61±3 | local |  | |
| 9 | LongCat-AudioDiT-1B · fp32 weights (official LongCat-AudioDiT repo, transformers>=5.3) | 60±6† | local | | |
| 10 |  Higgs Audio V3 TTS · bf16 | 59±6*† | local | | |
| 11 |  OmniVoice · fp32 | 59±3 | local | | |
| 13 | Qwen3-TTS 12Hz 1.7B Base · bf16 (qwen-tts) | 58±3 | local | | |
| 14 |  IndexTTS (v1) · fp32 on CPU (index-tts repo CLI `indextts`) | 57±7 | local | | |
| 16 |  F5-TTS v1 Base · fp32 | 56±6 | local | | |
| 17 | Fish Audio S2 Pro · bf16 (fish-speech official repo CLI) | 56±3 | local | | |
| 18 | Qwen3-TTS 12Hz 0.6B Base · bf16 (qwen-tts) | 56±4 | local | | |
| 19 | IndexTTS-2 · fp32 (index-tts repo) | 54±3 | local | | |
| 20 | ZipVoice · fp32 (ZipVoice repo) | 54±6 | local | | |
| 22 |  Fun-CosyVoice3-0.5B-2512 · fp32 (CosyVoice repo) | 53±3 | local | | |
| 23 | E2 TTS Base (F5-TTS reproduction) · fp32 | 53±4 | local | | |
| 27 |  Gemini 3.1 Flash TTS Preview | 53±7* | api $50.00/M chars | | |
| 28 | F5-TTS Base (v0) · fp32 | 52±6† | local | | |
| 30 | Higgs Audio V2 · mlx-8bit (mlx-audio) | 51±6*† | local | | |
| 33 | CosyVoice2-0.5B · fp32 (CosyVoice repo) | 48±3 | local | | |
| 35 |  Spark-TTS 0.5B · fp32 (Spark-TTS repo CLI) | 41±5 | local | | |
| 36 | CosyVoice-300M · fp32 (CosyVoice repo) | 40±5 | local | | |
| 40 |  XTTS v2 · fp32 (coqui-tts 0.27.5) | 23±6 | local | | |
| 41 |  StyleTTS 2 (LibriTTS) · fp32 (styletts2 PyPI package 0.1.6) | 17±7* | local | | |
| 42 | Tortoise TTS v2 · fp16 (neonbjb/tortoise-tts) | 12±7* | local | | |
| 43 | YourTTS · fp32 (coqui-tts) | -1±7*† | local | | |
| — |  Eleven Flash v2.5 | not yet calibrated | api $50.00/M chars | | |
| — | Eleven v3 | not yet calibrated | api $100.00/M chars | | |
| — |  Voxtral TTS (4B) · bf16 | not yet calibrated | local | | |
| — |  ZONOS2 8B · mlx-bf16 (mlx-audio) | not scored yet | local |
+ 17 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