VoiceStudio: Speech, Transcription, and Dubbing
Prepare local models, generate narration, and explore voice design, transcription, and video dubbing.
Open: Apps → Market → VoiceStudio → Install. Complete the system installer and launch it.
Third-party tool: VoiceStudio comes from a third-party open-source project. Nexts provides the install entry and launcher; the provider is responsible for the tool's features, accounts, fees, license, and support. See the project link at the end of this page.
VoiceStudio is a separate voice-production tool for narration, voice styles, transcription, and dubbing. Features depend on the engine, downloaded models, and installed version.
Features
| Feature | Use |
|---|---|
| Text to speech | Turn a script into audio |
| Voice cloning and design | Use authorized reference audio or describe a voice |
| Transcription | Convert recordings to text |
| Video dubbing | Translate and dub a video |
| Stories and audiobooks | Arrange voices and generation jobs for longer scripts |
| Model management | Download engines and models needed for a task |
Generate your first narration
- Choose an engine in model management and finish its download and initialization.
- Select an existing voice, or import a clear sample you are authorized to use for cloning.
- Enter a short script and choose a supported language and parameters.
- Generate, listen, and adjust the script or voice settings.
- Save or export the audio and check it in a player.
Result: a short usable narration before trying longer scripts or dubbing.
Common problems
- Slow first start: check model downloads and initialization.
- Generation fails: check engine support, memory, GPU memory, and model status.
- No sound: check the system output device and the exported file.
- Want spoken Nexts replies: configure Voice & Video. Installing VoiceStudio does not replace Nexts voice services.
Guides: VoiceStudio documentation · Project documentation.