LocalClaw/TTS/Maya-1
Local TTS model

Maya-1

Catalogue summary: Apache-licensed 3.30B text-to-speech model for description-based voice design and expressive inline controls. It predicts SNAC audio tokens, decodes 24 kHz mono speech locally, and ships official Transformers plus vLLM streaming reference paths with downloadable BF16 safetensors.

Repository editorial metadata; verify comparative claims in the linked upstream material.

GPU recommendedtext-to-speech generation1 languagesApache 2.0
Choose an app

Start with the recommended app, or choose another supported option.

Compare speech models
Open model filesRecommended verified starting pointOpen in UnslothLaunches Unsloth Desktop on this modelOpen Python packageVerified package page without exposing a commandOpen on Hugging FaceFiles, licence and model cardCheck my machineOptional: verify the fit with your saved hardware

Desktop app links require the app to be installed. If nothing opens, LocalClaw will show app-download and model-file fallbacks.

Catalogue quality
9.2/10
Catalogue speed
7.6/10
Model size
3.30B BF16 safetensors; official single-GPU recommendation is 16GB+ CUDA VRAM with BF16 support
Voices
Natural-language voice descriptions plus inline expressive controls

Can Maya-1 run locally?

Maya-1 can generate speech locally for private voice workflows. Use the verified setup options on this page; no terminal command is required to choose the right path.

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

Upstream source
voice-designemotionstreamingcontrollable

Audio profile

Cat. quality
9.2
Cat. speed
7.6
Audio
8.7

Best fit

Maya-1 is best for private local text-to-speech experiments and production prototypes.

Hardware: gpu

Model details

Type
Local TTS model
Family
maya
Latency
low
Formats
transformersvllmsafetensors
Languages
en
Context
Llama-style causal transformer, 3,300,928,512 parameters, SNAC 24 kHz decoder, batch Transformers example and vLLM streaming reference; no reference recording required, but accents, pronunciation and expressive control require representative testing

Install locally

01
Check runtimeConfirm the backend supports transformers, vllm, safetensors on your machine.
02
Open recommended setupUse the app and model links above. LocalClaw does not expose a terminal command.
03
Test locallyRun a short private audio prompt before moving into production workflows.

Good for

  • text-to-speech generation
  • GPU recommended local workflows
  • voice-design, emotion, streaming

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

Maya Research Maya 2 Native Local TTS model · Not rated Zyphra ZONOS2 Local TTS model · Q 9.6 · Speed 8.5 BreezeBlue Breeze TTS 2 Local TTS model · Q 9.6 · Speed 8.4 Zyphra Zonos v0.1 Local TTS model · Q 9.5 · Speed 8.5 Boson AI Higgs TTS 3 4B Local TTS model · Q 9.7 · Speed 8 OpenBMB VoxCPM2 Local TTS model · Q 9.4 · Speed 8.3 Bilibili IndexTTS 2 Local TTS model · Q 9.4 · Speed 8 DarkPs ICE-012 Audio Local TTS model · Q 9.1 · Speed 8.2
CompareBrowse all TTS models Local AIBrowse LLM models macOS appGet LocalClaw