Skip to content
SPECIFICTION
Get listed

VoiceStudio

voicestudio.sh

From $8.25/mo Free plan WebWindowsmacOSLinuxAPISelf-hosted
Visit voicestudio.sh
Spec score 8.8 #26 of 233 in Text-to-speech tools

What it is

VoiceStudio is an open-source voice AI studio for local voice cloning, voice design, video dubbing, dictation, transcription and audiobook creation. Users can describe a voice by gender, age, accent, pitch and emotion without providing reference audio. Its dubbing workflow transcribes and translates video, then re-voices it while keeping speakers separate and aligning timing with the original. Users can create multi-voice audio from scripts and chaptered audiobooks from long text or EPUB files. The desktop app exposes a local OpenAI-compatible API for speech, voices, transcription and dubbing. The maker lists 26 adapters, including local text-to-speech and transcription engines and a configured-remote ASR adapter. The maker says recordings, generated audio, transcripts and derived voice data stay on user-controlled storage and are not received by its website or control plane. The app may access the network for updates, model downloads or explicitly network-backed adapters. The public build has no hosted dashboard or Cloud API. Open Source costs nothing under AGPL-3.0; Pro costs $99 a year and Lifetime costs $299, paid once. Speech model licences are separate.

Spec sheet

Product
VoiceStudio is an open-source, local voice AI studio for voice cloning, voice design, video dubbing, dictation, transcription, and audiobook creation.Read 30 Sep 2026 · voicestudio.sh
Platforms
The download page lists desktop builds for macOS, Windows, and Linux and a Docker web studio for servers, homelabs, or GPU boxes.Read 30 Sep 2026 · voicestudio.sh
Free plan
YesRead 20 Sep 2026 · voicestudio.sh
Integrations
The desktop app exposes an OpenAI-compatible local API at http://localhost:3900/v1 with speech, voices, transcription, and dubbing endpoints.Read 30 Sep 2026 · voicestudio.sh
Privacy
The maker says local recordings, generated audio, transcripts, and derived voice data are stored on user-controlled storage and are not received by its website or control plane.Read 30 Sep 2026 · voicestudio.sh
Maker
The site says VoiceStudio was designed and built by Palash.dev, whose about page names Palash Debnath and describes him as based in Agartala, India; the opened pages give no founding year.Read 30 Sep 2026 · palash.dev
API access
YesRead 20 Sep 2026 · voicestudio.sh
Audiobooks and stories
Users can create multi-voice audio from scripts and chaptered audiobooks from long text or EPUB files.Read 30 Sep 2026 · voicestudio.sh
Cloud status
Cloud is in early access and invites users to request access for free usage credits; the public build does not offer the hosted dashboard or Cloud API.Read 30 Sep 2026 · voicestudio.sh
Commercial use
YesRead 20 Sep 2026 · voicestudio.sh
Commercial use and licensing
The maker says VoiceStudio may be used at work or for money under AGPL-3.0, while speech models have separate licences and some may be research-only.Read 30 Sep 2026 · voicestudio.sh
Engine catalog
The maker lists 26 adapters, including local text-to-speech and transcription engines plus a configured-remote OpenAI-compatible ASR adapter.Read 30 Sep 2026 · voicestudio.sh
Export formats
mp3,opus,aac,flac,wav,pcmRead 20 Sep 2026 · voicestudio.sh
Hardware
The download FAQ says about 8 GB RAM and around 10 GB disk for models, recommends 16 GB or more RAM, and says GPU is optional but CPU use is slower.Read 30 Sep 2026 · voicestudio.sh
Network behavior
The app can access the network to check for updates, download models, or use an explicitly network-backed adapter.Read 30 Sep 2026 · voicestudio.sh
Video dubbing
The dubbing workflow transcribes, translates, and re-voices video while keeping speakers separate and aligning timing with the original.Read 30 Sep 2026 · voicestudio.sh
Voice cloning
The desktop app clones a voice from a short clean audio clip, with about three seconds usually enough.Read 30 Sep 2026 · voicestudio.sh
Voice design
Users can describe a voice by gender, age, accent, pitch, and emotion in a sentence without providing reference audio.Read 30 Sep 2026 · voicestudio.sh

Plans and prices

Open Source Free AGPL-3.0 · No seat count or evaluation period · Speech model licences are separate Read 30 Sep 2026 · voicestudio.sh
Pro $99 a year $99 per user / year 1 user · 3 active devices · 3 concurrent uses Read 30 Sep 2026 · voicestudio.sh
Lifetime $299, paid once $299 per user · one-time 1 user · 3 active devices · 3 concurrent uses Read 30 Sep 2026 · voicestudio.sh
Enterprise Priced on request Custom Flexible terms for larger teams · Enquiry is not a purchase, quote, agreement, or licence grant Read 30 Sep 2026 · voicestudio.sh

Every VoiceStudio plan and price →

Strong points and limits

Strong points

  • Voice design works without reference audio.
  • Dubbing separates speakers and aligns original timing.
  • Local API covers speech, voices, transcription and dubbing.
  • Exports include MP3, Opus, AAC, FLAC, WAV and PCM.
  • Pro is $99 a year.

Limits

  • Public build lacks a hosted dashboard and Cloud API.
  • Speech model licences are separate; some may be research-only.
  • The app can access the network for updates and downloads.
  • Recommended memory is 16 GB or more.

Who it suits

VoiceStudio suits people who want local tools for voice creation, dubbing, transcription or audiobook production, with an API and support for commercial use under AGPL-3.0. Users should check each speech model's separate licence, since some may be research-only.

Verdict

VoiceStudio brings voice creation and media workflows together in a local studio, with a local API and user-controlled storage. Check model licences and hardware needs, and note that hosted Cloud features are not in the public build.

Where Specifiction places it

Alternatives to VoiceStudioAll alternatives →