Inflect (offline, lightweight English)

What it does

Voices

In the Speakers tab, choose Inflect 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.

2 voices in 1 language.

• en-us 2

Both voices are the same synthetic American man, made by the model's author without a real person's recordings: Micro sounds a little more natural, Nano is smaller and faster. Inflect does not clone voices. To dub in the speaker's own voice, choose a voice-cloning engine such as Sopro or Chatterbox.

Each line is spoken with the same seed every time, so dubbing a line again in the same voice gives the same audio.

Models

The models are not inside the add-on. Each one downloads into Subtitld's shared model cache the first time its voice speaks, 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 models.

The add-on runs the ONNX build that Inflect's author publishes, without PyTorch. We checked it against the author's own code on the same lines: the same sounds for all 412 sentences of the author's test set, and the same audio for both models.

Options

In Settings › Add-ons › Inflect (offline, lightweight English) › Configure.

Languages

English only. Any English project (American, British, Australian…) is read with the American voice. A project in another language gets a message that says so: pick another dubbing engine for it.

Numbers, prices, dates, times and common abbreviations are read out as words: "$3.50" becomes "three dollars and fifty cents". Rare names, places and words from other languages may be mispronounced.

• en-us

Platforms

Linux x86-64 (any distribution from 2018 on), 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 both models and dubs with them.

Troubleshooting

• network_unavailableThe model couldn't be downloaded, or a downloaded file failed its check and was discarded. Check your connection and try again: the download resumes.
• disk_fullNot enough disk space for the model: 38 MB for Micro, 16 MB for Nano.
• unsupported_languageThe project's language is not English, 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. Write the subtitle and dub it again.
• out_of_memoryThe computer ran out of memory. Close other programs: Inflect needs about 300 MB.
• internalSomething failed inside the add-on; the message has the details.

License

Fine for commercial work. The Inflect v2 models and the author's code are Apache-2.0. The add-on is GPL-3.0-or-later because it includes espeak-ng, which turns text into sounds; its full source, espeak-ng's included, is on each release. The license covers the add-on, not what you make with it: the dubs you make are yours. The model's author asks that its speech never be passed off as a real person's recording.