Voice & audio
ComfyUI-OmniVoice-TTS
600+ languages of speech synthesis, inside ComfyUI
★ 548
June 2026
Apache-2.0
Voice & audio
What we checked ourselves
Not copied from the project's own blurb. These are things we opened and verified, with the date.
- 9 Sept 2026We checked that the link to the project still resolves.
- 14 Aug 2026We read the licence text itself (LICENSE). No unusual restrictions were stated.
- 1 Sept 2026We read the project's own documentation and found no sign that development has stopped.
Where this sits among the 119 tools we list in Voice & audio
- No API key required114 of 119
- Commercial use confirmed as allowed56 of 119
- Requires terminal commands93 that do not →
- Sends your input to the provider31 that do not →
Only 53 of the 119 meet all of the conditions above.
Counted from our own checks: every tool we list is examined against the same criteria.
What it does
Zero-shot TTS nodes with unusually broad language coverage, cloning a voice from three to fifteen seconds of reference audio, designing one from a text description of gender, age, pitch and accent, and generating multi-speaker dialogue. A hosted demo was running on 2026-08-18. Three seconds is all it takes to imitate someone, so restrict cloning to your own voice or one with explicit consent and label what you publish. Requires ComfyUI. Apache-2.0.
Summary based on the project's own description. The Japanese page has a fuller beginner guide: setup difficulty, what to prepare, and a step-by-step start.
Screenshots & visuals
Before you start
- Setup difficultySome setup needed
- Command lineRequired
- API keyNot required
- Sends data onlineYes
Judged automatically from the project's own metadata. Always confirm on the official page.
Before you use someone else's face or voice
Recreating a person's face or voice without their informed consent, and publishing material that shows them saying or doing something they did not, can amount to defamation or a violation of personality and publicity rights, with civil and criminal consequences. Sexual content, or impersonation for financial gain, is treated far more seriously. Work only with your own likeness, or with material where the person has agreed to both the content and where it will appear. Running the tool locally protects your data - it does not make publishing the result lawful.
ComfyUI-OmniVoice-TTS FAQ
- Is ComfyUI-OmniVoice-TTS free?
- Yes. It runs on your own machine, so there is no usage-based cost either.
- Do I need to install anything or write code to use ComfyUI-OmniVoice-TTS?
- It needs the command line. If you are not comfortable typing commands, expect to get stuck during setup.
- Does ComfyUI-OmniVoice-TTS work on a phone?
- No. It needs a computer.
- Can I use ComfyUI-OmniVoice-TTS commercially?
- The licence is Apache-2.0, which permits commercial use. Conditions such as keeping the copyright notice still apply, so read the licence text before shipping it inside something.
How it compares
The conditions that decide whether you can actually use it, side by side.
| Tool | Command line | API key | Sends data out | Phone | Commercial use |
|---|---|---|---|---|---|
| ComfyUI-OmniVoice-TTS (this page) | Required | Not needed | Yes | No | Yes |
| Chatterbox | Not needed | Not needed | Yes | No | Yes |
| Real-Time-Voice-Cloning | Required | Not needed | Yes | No | Not verified |
| Coqui TTS | Required | Not needed | No | No | Yes |
"Sends data out" means your input is uploaded to someone's server. Pick "No" when the material cannot leave your organisation.