Skip to content
SPECIFICTION
Get listed

UtaForge AI

github.com

WindowsmacOS
Visit github.com
Spec score 6.8 #51 of 55 in AI song cover generators

Spec sheet

Purpose
UtaForge AI is an open-source tool that generates VOICEVOX singing covers and lyric videos from audio and lyrics.Read 11 Oct 2026 · github.com
Intended users
The README asks users to confirm they have rights to the music, lyrics, voices, images, characters, and generated works they use.Read 4 Oct 2026 · github.com
Platforms
The stated operating system requirements are macOS 13 or later and Windows 11; Python 3.11 or 3.12 is also required.Read 11 Oct 2026 · github.com
Integrations
The project requires a running VOICEVOX ENGINE and ffmpeg, and supports audio-separator or Demucs for source separation.Read 11 Oct 2026 · github.com
Privacy
Inputs, lyrics, artwork, generated files, and external models are stored on local disk; the README says project and work directories are excluded from Git by default.Read 11 Oct 2026 · github.com
License
The source code is distributed under the MIT License.Read 11 Oct 2026 · github.com
Audio analysis
It analyzes vocal pitch, volume, and lyric timing and transfers singing characteristics to VOICEVOX output.Read 11 Oct 2026 · github.com
Data handling
The security policy says inputs, lyrics, images, generated files, and external models are stored on local disk, and advises checking project and cache contents before sharing.Read 4 Oct 2026 · github.com
Exports
It can export MP3 audio, VOICEVOX .vvproj projects, UtaFormatix .ufdata, and MP4 video.Read 11 Oct 2026 · github.com
Interfaces
It provides both a browser-based Studio and a command-line interface.Read 11 Oct 2026 · github.com
Local processing
The tool runs locally and does not require external web services.Read 11 Oct 2026 · github.com
Lyrics
Lyrics can be provided as text, Markdown, or LRC, and timing can be edited over a waveform.Read 4 Oct 2026 · github.com
Lyrics and editing
Lyrics can be provided as text, Markdown, or LRC, with line and mora timing editable on a waveform.Read 11 Oct 2026 · github.com
Project status
The project is marked alpha, and its specification, project format, and output quality may change.Read 4 Oct 2026 · github.com
Project status and limits
The project is alpha, and its specifications, project format, and output quality may change.Read 11 Oct 2026 · github.com
Requirements
The README lists macOS 13 or later or Windows 11, plus Python 3.11 or 3.12, as requirements.Read 4 Oct 2026 · github.com
Security reporting
The security policy supports only the latest main branch and asks users to report vulnerabilities through GitHub private vulnerability reporting.Read 11 Oct 2026 · github.com
Security support
The security policy supports only the latest main branch and directs vulnerability reports through GitHub’s private vulnerability reporting.Read 4 Oct 2026 · github.com
Video
It can create subtitled MP4 videos in 9:16 or 16:9 formats, with PSD-based lip-sync and facial expressions or a still image.Read 4 Oct 2026 · github.com
Video features
It can generate subtitled MP4s in vertical 9:16 or widescreen 16:9 formats, with PSD-based lip-sync, blinking, and facial expressions.Read 11 Oct 2026 · github.com

Where Specifiction places it

Alternatives to UtaForge AIAll alternatives →