VivaDictaVivaDicta
← All releases

3.2.0

May 1, 2026

The interpreter earpiece used to come with a UN seat. Now you just need an iPhone. VivaDicta 3.2 introduces Live Translation - real-time speech-to-speech across 60+ languages. Two new cloud transcription providers join the lineup, and Soniox, Gladia, and Speechmatics now translate as they transcribe in a single step. See the Live Translation and Translation docs for more.

Live Translation

  • Your own personal interpreter - the kind of real-time translation that used to mean an earpiece in a UN booth, now in your pocket
  • Tap the new globe icon at the top of the notes list to start a session
  • Speak in one language and hear it in another, in near real time
  • 60+ languages, any-to-any source/target pair
  • Plug in headphones, choose from 12 multilingual voices, and adjust playback speed
  • Save the session as a note when you're done
  • Powered by Soniox - add a Soniox API key in Settings to enable

Translate While You Transcribe

  • With Soniox, Gladia, or Speechmatics selected, pick a target language in the new "Translate to" picker
  • Your transcription comes back already translated, in a single step
  • No extra AI processing required - the translation is done by the transcription provider itself
  • Original transcript is still saved alongside the translation

Two New Cloud Transcription Providers

  • Gladia Solaria - 100+ languages, speaker labels, inline translation. New accounts get free credits
  • Speechmatics Enhanced - industry-leading accuracy on European languages, with speaker labels and built-in translation across 50+ languages

Trim Trailing Period

  • New per-mode toggle in Edit Mode → Text Processing
  • Strips trailing "." or "..." from the final transcript
  • Helpful for casual messaging where "Okay." can read as cold or passive-aggressive
  • "!" and "?" are kept - they carry their own meaning
  • Off by default; opt-in per mode

Multilingual Filler Filtering

  • Filler words are now also stripped in Russian (ээ, э-э, эм), Spanish (ehm), German (äh, ähm), and French (euh)
  • Triggered when the mode language is set or auto-detected to one of these
  • Universal fillers ("uh", "um", "hmm") continue to be stripped regardless of language

Save to Obsidian Automatically

  • Turn on Append to Obsidian in any mode
  • Each transcription opens Obsidian with a new note
  • One note per transcription with timestamped filenames by default
  • Or set the filename to {date} to pile them into a daily note

Reminders in Original Language

  • Extract Reminders now keeps the original language of your note
  • German notes produce German reminders, Russian notes produce Russian reminders, instead of occasionally being translated to English