VOICEVOX review
A free, open-source voice tool with unusually detailed pronunciation and timing controls.
Reviewed by iTechGuides Editors · Editorial team · Updated Oct 2026
VOICEVOX is free text-to-speech software for creating narrated audio with character-based voice libraries. It is suited to creators, developers, and teams that want direct control over pronunciation, accents, intonation, timing, and speaking styles without a subscription price. The desktop application runs on Windows, macOS, and Linux, while the engine can generate speech for other applications and services. Commercial use is permitted under the software terms, with additional conditions possible for individual voice libraries.
Its strongest differentiator is the level of voice editing available in a free application. Users can adjust pronunciation and accents in detail, tune intonation and timing per sound, and select multiple speaking styles for supported characters. VOICEVOX also includes voice morphing between supported voices, a custom pronunciation dictionary, WAV export, and experimental humming and singing synthesis. This makes it a practical fit for narrated audio where pronunciation and delivery need more adjustment than a basic text-to-speech workflow provides. The experimental status of the humming and singing features makes them better suited to exploratory use than as the sole basis for a production workflow.
For technical workflows, VOICEVOX offers an engine API, executable and Docker distributions, and a core library for integration into applications and services. That gives developers several ways to connect speech generation to existing software, while the desktop apps support direct creation. The main trade-off is format flexibility: the listed export format is WAV. Voice-library terms and credit requirements also need review before commercial release. Choose VOICEVOX for free character-voice synthesis, detailed pronunciation control, and open-source integration options; consider an alternative if you need other export formats or a less experimental singing workflow.
VOICEVOX pros and cons
- Where it wins
- Free, open-source software with permitted commercial use
- Detailed pronunciation, accent, intonation, and timing controls
- Desktop apps, API access, Docker, and WAV export
- Where it doesn't
- Audio export is limited to WAV
- Humming and singing synthesis are experimental
- Voice libraries may add credit and usage requirements
VOICEVOX fact sheet, pricing and score →
Advertiser disclosure: iTechGuides is reader-supported. Vendors can pay for top positions in our rankings and for a place on other products' pages, and we may earn a commission when you click some links. Bought places stand at the number bought; this page and our disclosure say so. Paying vendors may get a fuller, more detailed review from our editors, and that review can change their score. How we rank.
Last updated · How we research and update