LocalClaw/TTS/Dots TTS MF
Local TTS model

Dots TTS MF

2B fully continuous end-to-end autoregressive TTS system with zero-shot voice cloning. The MF checkpoint distills dots.tts-soar with MeanFlow for few-step, low-latency inference at 48 kHz, while keeping strong speaker similarity and natural prosody. Apache 2.0.

GPU recommended text-to-speech generation 24 languages Apache 2.0
Compare TTS models Open source page
Quality
9.4/10
Speed
8/10
Model size
4.2 GB
Voices
Zero-shot voice cloning from reference audio + transcript

Can Dots TTS MF run locally?

Dots TTS MF can generate speech locally for private voice workflows. Start with python -m pip install "git+https://github.com/rednote-hilab/dots.tts.git".

Apache 2.0 license. Still verify upstream usage notes before shipping.

python -m pip install "git+https://github.com/rednote-hilab/dots.tts.git" Upstream source
cloningmultilingualcontrollablerealtime

Audio profile

Quality
9.4
Speed
8
Local
8.8

Best fit

Dots TTS MF is best for local voice cloning and expressive speech generation.

Hardware: gpuapple

Model details

Type
Local TTS model
Family
dots
Latency
low
Formats
pytorchsafetensorsmlx
Languages
en, zh, yue, ja, ko, fr, de, es, it, pt, nl, ru, uk, pl, cs, ro, el, fi, tr, ar, hi, vi, id, th
Context
2B AR flow-matching TTS, 48 kHz AudioVAE, MeanFlow distilled, recommended NFE=4

Install locally

01
Check runtimeConfirm the backend supports pytorch, safetensors, mlx on your machine.
02
Install modelUse the upstream command or repository instructions.
03
Test locallyRun a short private audio prompt before moving into production workflows.
python -m pip install "git+https://github.com/rednote-hilab/dots.tts.git"

Good for

  • text-to-speech generation
  • GPU recommended local workflows
  • cloning, multilingual, controllable

Watch before shipping

  • Validate pronunciation, latency and artifacts with your own voice samples.
  • Review the upstream license and acceptable-use notes.
  • Benchmark on your target CPU, Apple Silicon or GPU setup.

Related TTS and speech models

OpenBMB VoxCPM2 Local TTS model · Q 9.4 · Speed 8.3 MyShell OpenVoice V2 Local TTS model · Q 8.9 · Speed 9 Speech Research (SWivid) F5-TTS v1.1 Local TTS model · Q 9.5 · Speed 9.2 Zyphra Zonos v0.1 Local TTS model · Q 9.5 · Speed 8.5 Alibaba FunAudioLLM CosyVoice 2 Local TTS model · Q 9.3 · Speed 8.8 MYShell MeloTTS Local TTS model · Q 9 · Speed 9 OpenMOSS / MOSI.AI MOSS-TTS-Nano Local TTS model · Q 8.5 · Speed 9.7 Fish Audio Fish Speech Local TTS model · Q 9 · Speed 8.5
CompareBrowse all TTS models Local AIBrowse LLM models macOS appGet LocalClaw