VOICEVOX

Spec sheet

Purpose

VOICEVOX is software for text-to-speech and singing voice synthesis.Read 12 Oct 2026 · voicevox.hiroshiba.jp

Platforms

Windows,macOS,Linux,APIRead 20 Sep 2026 · voicevox.hiroshiba.jp

Free plan

YesRead 20 Sep 2026 · voicevox.hiroshiba.jp

Support

The FAQ directs users to post questions or requests with #VOICEVOX on X and asks bug reporters to contact the VOICEVOX account there.Read 12 Oct 2026 · voicevox.hiroshiba.jp

API access

YesRead 20 Sep 2026 · voicevox.hiroshiba.jp

Audio export

Generated audio can be exported as WAV files.Read 12 Oct 2026 · voicevox.hiroshiba.jp

Characters

The site lists multiple character voices, and says usage rules vary by character.Read 12 Oct 2026 · voicevox.hiroshiba.jp

Commercial use

YesRead 20 Sep 2026 · voicevox.hiroshiba.jp

Engine integration

The VOICEVOX engine can generate audio from other software or applications and is distributed as executables and a Docker image.Read 12 Oct 2026 · voicevox.hiroshiba.jp

Export formats

WAVRead 20 Sep 2026 · voicevox.hiroshiba.jp

GPU limits

GPU mode supports DirectML GPUs on Windows and Nvidia GPUs on Linux; macOS does not support GPU mode.Read 12 Oct 2026 · voicevox.hiroshiba.jp

Library integration

The VOICEVOX CORE library is offered for embedding speech synthesis in applications and services.Read 12 Oct 2026 · voicevox.hiroshiba.jp

License conditions

The FAQ says generated audio can be used commercially or non-commercially with credit, subject to VOICEVOX and each character's terms.Read 12 Oct 2026 · voicevox.hiroshiba.jp

Offline use

The FAQ says VOICEVOX can be used on an offline computer.Read 12 Oct 2026 · voicevox.hiroshiba.jp

Open source

The site says VOICEVOX is built on an open-source version and invites users to contribute improvements.Read 12 Oct 2026 · voicevox.hiroshiba.jp

Platform requirements

The FAQ lists Windows 10 or 11, macOS 14 or later, and Ubuntu 22.04 or 24.04 for the CPU version.Read 12 Oct 2026 · voicevox.hiroshiba.jp

Singing

The prototype song feature offers humming in a character's speaking voice and a separate singing voice mode.Read 12 Oct 2026 · voicevox.hiroshiba.jp

Song feature limit

The song feature is described as a prototype under active development; its FAQ says each note currently accepts only one Japanese character and overlapping notes cause errors.Read 12 Oct 2026 · voicevox.hiroshiba.jp

Speech controls

Users can adjust intonation, accents, speaking speed, pitch, volume, and pauses.Read 12 Oct 2026 · voicevox.hiroshiba.jp

Plans and prices

Every VOICEVOX plan and price →

Where Specifiction places it

• Text-to-speech tools#57 of 2338.5
• Text-to-Speech Software#128 of 2237.9