# VoiceStudio

VoiceStudio (formerly OmniVoice Studio) is an open-source, mainly local desktop speech AI tool for creators, developers, and teams needing dubbing, voice cloning, video localization, dictation transcription, and audiobook production. It concentrates many speech tasks in a desktop app for users who want to process speech on-device. Import short audio to build a cloned voice, or design new voices from text descriptions; after uploading video, the platform can transcribe, translate, and re-dub while handling speakers and timing. Long scripts or EPUB can make multi-character audiobooks; audio and video can also become editable, searchable text. The page shows the voice catalog covers many languages, with exact range depending on the engine used. Core features Local voice clone and design: upload a short voice sample to create a cloned timbre, or design new voices by gender, age, accent, pitch, and emotion. Video translation and dubbing: import video for speech transcription, content translation, and re-dubbing while trying to keep speaker segments and original timing. Audio/video transcription: turn audio or video into editable, searchable text for interviews, meetings, courses, and video materials. Multi-character audiobook production: import long scripts or EPUB, assign voices to roles, and generate chaptered audiobook content.

VoiceStudio (formerly OmniVoice Studio) is an open-source, mainly local desktop speech AI tool for creators, developers, and teams needing dubbing, voice cloning, video localization, dictation transcription, and audiobook production. It concentrates many speech tasks in a desktop app for users who want to process speech on-device. Import short audio to build a cloned voice, or design new voices from text descriptions; after uploading video, the platform can transcribe, translate, and re-dub while handling speakers and timing. Long scripts or EPUB can make multi-character audiobooks; audio and video can also become editable, searchable text. The page shows the voice catalog covers many languages, with exact range depending on the engine used. Core features Local voice clone and design: upload a short voice sample to create a cloned timbre, or design new voices by gender, age, accent, pitch, and emotion. Video translation and dubbing: import video for speech transcription, content translation, and re-dubbing while trying to keep speaker segments and original timing. Audio/video transcription: turn audio or video into editable, searchable text for interviews, meetings, courses, and video materials. Multi-character audiobook production: import long scripts or EPUB, assign voices to roles, and generate chaptered audiobook content.

Canonical: https://uniquebase.ai/products/voicestudio
Stable identifier: UB-D6782
Snapshot captured: 2026-10-28T00:47:51.550Z
English updated: 2026-10-28T00:56:10.046Z

## Connected profiles

- [VoiceStudio](/companies/voicestudio)

## Sources

- No source links are available for this profile.