OmniVoice

Purpose: Running multilingual text-to-speech, voice cloning, and voice design locally without relying on a hosted service.

Inferred · not functionally tested

Audience: developers and AI enthusiasts running local speech models

Inferred · not functionally tested

Functions: voice_synthesis

Inferred · not functionally tested

Interfaces: API: unknown · MCP: unknown · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)

Recorded constraints: pricing: open_source · license: MIT · platforms: CLI, WEB · deployment: browser, cli, self_hosted, macos, windows, linux

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: huggingface.co · github.com. These links do not verify the individual claims.

OmniVoice sits in PulseGate's Text to speech category. Inferred · not functionally tested: It focuses on running multilingual text-to-speech, voice cloning, and voice design locally without relying on a hosted service. Inferred · not functionally tested: It is built as an open-source project for developers and AI enthusiasts running local speech models. Basis unknown · not verified: OmniVoice is open source under the MIT license. Basis unknown · not verified: OmniVoice is available on the web, the command line, macOS, Windows, and Linux, and it can be self-hosted.

Behind OmniVoice is Serveurperso, and it first shipped in 2026. Development happens publicly on GitHub with 156 stars and 38 commits in the last 90 days. Inferred · not functionally tested: Key capabilities include text to speech, voice cloning, and voice design.

Summary written by a language model from the project’s public pages.