Sopro (offline, voice clone, 4 languages)

What it does

Before you install

Sopro asks little of your computer:

• Disk: about 340 MB for the model, downloaded on the first line.
• Memory: about 1 GB while it speaks.
• Processor: any 64-bit Intel or AMD processor, or Apple Silicon. No graphics card is used.

Clone a voice only with its owner's consent. Sopro's author asks that it never be used to pass as someone else.

Voices

In the Speakers tab, choose Sopro as a speaker's Dubbing engine, then pick a Voice. Turn on Fit dub to subtitle duration for the speaker to stretch or squeeze each line to its subtitle.

9 voices.

With Speaker's own voice, Subtitld cuts a sample of that speaker from the project's audio, from one of their subtitles or several short ones joined. If you have separated music from voice for this video, the sample comes from the voice alone. The Fallback reference clip in the add-on's settings is used only when no sample can be cut. The best sample is 5 to 20 seconds of the speaker alone, with no music or other voices.

Each preset is a LibriVox volunteer reading a book in that language. Every preset speaks all four languages; its own language only gives it an accent, so pick one from your project's language for the most natural dub.

Models

Sopro has one model for all four languages. It is not inside the add-on: it downloads into Subtitld's shared model cache the first time you dub, from Hugging Face at a pinned revision, each file checked. An interrupted download resumes where it stopped. Updating or removing the add-on keeps the model.

The add-on runs the ONNX build of Sopro that its author publishes, without PyTorch. We checked it against the official PyTorch build on the same lines in all four languages: it made no more mistakes and sounded as close to the speaker.

Options

In Settings › Add-ons › Sopro (offline, voice clone, 4 languages) › Configure.

Languages

English, European Portuguese, French and German. Brazilian Portuguese text is read too, with a European accent. A project in any other language gets a message that says so: pick another dubbing engine for it.

Write numbers and symbols as words where it matters: Sopro reads "1 + 2" less reliably than "one plus two". A word from another language inside a sentence may be mispronounced.

• en
• pt
• fr
• de

Platforms

Linux x86-64, macOS on Apple Silicon and Windows x86-64. Each release is built on all three, and on each one CI installs the add-on as Subtitld does, downloads the model and dubs with it.

Troubleshooting

• network_unavailableThe model couldn't be downloaded. Check your connection and try again: the download resumes.
• disk_fullNot enough disk space for the model, about 340 MB.
• unsupported_languageThe project's language is not one of the four, or not set. Set it in the project, or pick another dubbing engine.
• unsupported_voiceThe project names a voice this version doesn't have. Pick the voice again in the Speakers tab.
• bad_paramsThe line has no text, or the cloned voice got no sample: open the video, or set a Fallback reference clip. The message says which.
• out_of_memoryThe computer ran out of memory. Close other programs: Sopro needs about 1 GB.
• internalSomething failed inside the add-on; the message has the details.

License

Fine for commercial work: the add-on, Sopro and the Sopro V2 Turbo model are Apache-2.0. The preset voices are LibriVox recordings, in the public domain; the English ones come through LibriTTS-R, under CC-BY-4.0, and the add-on credits each one. The dubs you make are yours.