BATS - Subtitle2Speech

Also available in:

Deutsch

Let existing VisTitle subtitles be spoken – English AI voice, Nvidia GPU

Subtitle2Speech gives your existing subtitles a voice: the preset reads a VisTitle subtitle file (.vtsubtle) and produces a WAV file from it using the AI voice engine Kokoro (Nvidia GPU) – in a choice of US or UK English voices, with the time slots of the subtitles. Ideal for creating an English voice-over pass from filmed material with subtitles, without typing the text in again.

Adding the menu entry

“Subtitle2Speech” is added through the “Add function...” assistant (right-click in the BIN → Add function... → pick Subtitle2Speech - Create English Voice). The assistant’s questions:

  1. Voice (“Please select the voice. English only.”): Heart (American, female), Michael (American, male), Lily (British, female) or George (British, male).
  2. Max. stretch (0–50 %, default 10 %): speech-rate adjustment to fit the sentences into the subtitles’ time slots; recommended below 15 %, 0 % = off.
  3. Add result to the BIN? – assistant note: this preset works on the trimmed version (IN/OUT) of the selected file. Yes → additionally registered under __BAT Server\Speech.
  4. Placement (BIN or timeline) and name (suggestion: “Vtsubtle read by <voice>”), then [Preview '.bat0' file] / [Add menu entry].

How to use it

  1. Right-click the clip for which a VisTitle subtitle file (.vtsubtle) exists → Generate Speech submenu → your entry (e.g. “Vtsubtle read by Heart”).
  2. Kokoro speaks the subtitle texts with the time slots of the .vtsubtle file; the finished WAV file is registered in the BIN (additionally under __BAT Server\Speech if chosen) – including the clip’s frame rate and time stamps.

Good to know

  • Source = VisTitle file: the preset reads .vtsubtle files – the subtitles created in EDIUS/VisTitle, for example. Plain SRT files are handled by Convert2Speech instead (which can also transcribe audio).
  • English only: the four Kokoro voices speak US or UK English – even if the subtitle texts are written in another language, the engine reads them “in English”.
  • Stretch in moderation: longer sentences in short time slots are stretched up to the set limit – below 15 % the result stays natural sounding.
  • Nvidia GPU: Kokoro runs on the Nvidia GPU; without a suitable GPU the entry is not really usable.

Managing the preset

Entries created via the assistant are user presets: the .bat0 file lives under C:\ProgramData\EdiusPowerTools\BAT-server\bat_files\BIN\ or …\bat_files\timeline\ depending on your choice, and can be freely edited, renamed or deleted (deleting removes the context-menu entry). Voice and stretch value are baked into the .bat0 – changes take effect from the next run.