Skip to content
SPECIFICTION
Get listed

MetaVoice

github.com

WebLinuxAPISelf-hosted
Visit github.com
Spec score 7.6 #33 of 43 in AI voice cloning tools

Spec sheet

Product
MetaVoice-1B is an open-source foundational text-to-speech model.Read 9 Oct 2026 · github.com
Deployment
The README says it can be deployed on AWS, GCP, or Azure, or used locally with the reference implementation.Read 9 Oct 2026 · github.com
License
The model is released under the Apache 2.0 license.Read 9 Oct 2026 · github.com
Access
The README links to use through Hugging Face and a Google Colab demo.Read 9 Oct 2026 · github.com
API and deployment
The project provides an inference server with API documentation at its /docs route and says it can be deployed on AWS, GCP, or Azure.Read 9 Oct 2026 · github.com
Fine-tuning
The repository supports fine-tuning its first-stage language model and says it has succeeded with as little as one minute of training audio for Indian speakers.Read 9 Oct 2026 · github.com
Hardware requirement
Installation requires a GPU with at least 12 GB of VRAM and Python version 3.10 or later but below 3.12.Read 9 Oct 2026 · github.com
Interfaces
The repository provides a web UI and an inference server with API definitions available at the server's /docs URL.Read 9 Oct 2026 · github.com
Local use
The model can be downloaded and run locally through the reference implementation.Read 9 Oct 2026 · github.com
Model scale
The model has 1.2 billion parameters and was trained on 100,000 hours of speech.Read 9 Oct 2026 · github.com
Open-source model
MetaVoice-1B is a 1.2-billion-parameter text-to-speech model trained on 100,000 hours of speech and released under the Apache 2.0 license.Read 9 Oct 2026 · github.com
Optional integration
The fine-tuning workflow offers optional Weights & Biases logging.Read 9 Oct 2026 · github.com
Organization
GitHub identifies the MetaVoice organization as based in the United States; the opened maker pages do not state its headquarters city or founding year.Read 9 Oct 2026 · github.com
Performance
The README says that on Ampere, Ada-Lovelace, and Hopper GPUs, synthesis runs faster than real time after model compilation.Read 9 Oct 2026 · github.com
Product status
The GitHub-linked metavoice.io site redirects to Familiar, which describes a duplex speech model for outbound sales calls and offers a 30-day pilot.Read 9 Oct 2026 · metavoice.io
Security and privacy
The repository describes the model and code as open source but does not state security certifications or data-handling commitments.Read 9 Oct 2026 · github.com
Speech style
The project lists emotional speech rhythm and tone in English as a design priority.Read 9 Oct 2026 · github.com
Text length
The README describes synthesis of arbitrary-length text.Read 9 Oct 2026 · github.com
UI input limit
The included web UI accepts up to 220 characters of text and truncates longer input.Read 9 Oct 2026 · github.com
Voice cloning
It supports zero-shot cloning of American and British voices from 30 seconds of reference audio.Read 9 Oct 2026 · github.com
Voice generation
The model targets emotional speech rhythm and tone in English, zero-shot cloning of American and British voices using 30 seconds of reference audio, and long-form synthesis.Read 9 Oct 2026 · github.com
Voice upload limits
The web UI asks for a clean, single-speaker sample of 30 to 90 seconds without background noise, and its code enforces a 50 MB upload-size ceiling.Read 9 Oct 2026 · github.com
Web interface
The repository includes a Gradio web UI with preset voices and an option to upload a target voice sample for cloning.Read 9 Oct 2026 · github.com

Where Specifiction places it

Alternatives to MetaVoiceAll alternatives →