VivaDictaVivaDicta
← All releases

3.8.0

August 9, 2026

Your words, ready the moment you stop talking. VivaDicta 3.8.0 adds Soniox Realtime, which transcribes while you speak instead of after you stop, and finally records through your AirPods and Bluetooth headsets. Plus Grok subscription sign-in, language-aware filler removal, and a broad refresh of the transcription and AI model lineup.

Soniox Realtime

  • A new transcription model that streams your speech to Soniox while you talk, instead of uploading the recording after you stop - the text is ready almost the moment you finish
  • Pick "Soniox Realtime" in the model list to use it
  • If the connection drops it quietly falls back to the normal upload, so nothing is lost
  • The standard Soniox model also returns results with noticeably less waiting after you stop recording

Your Headphones' Microphone

  • If you're wearing AirPods or a Bluetooth headset, VivaDicta now records through them instead of falling back to the iPhone microphone - the same way Phone and Voice Memos behave
  • A new Microphone setting lets you pin the iPhone microphone instead, which keeps your headphones in full-quality audio while you dictate
  • On iOS 26, recording uses Apple's high-quality Bluetooth mode where supported, so music and podcasts no longer drop to muffled headset sound
  • Keyboard text actions no longer switch your headphones into low-quality headset mode when nothing is being recorded

Sign In With Grok

  • Connect a SuperGrok or X Premium account and use Grok for AI processing without an API key
  • Sign-in happens in the browser with a short code, the same way you'd connect a TV app
  • xAI limits which plans can connect an app, so an API key is still there as a fallback and unlocks the full model list

Smarter Filler Removal

  • Hesitation sounds like "uh" and "um" are now removed based on the transcript's language, so real words are no longer stripped by mistake
  • German "um" (as in "um zu") and Portuguese "um" now stay intact
  • A new "Remove Filler Words" toggle in Settings > Advanced turns the cleanup off entirely and keeps every word exactly as spoken

New Transcription Models

  • AssemblyAI Universal-3.5 Pro is now the default AssemblyAI model, with native code switching for multilingual speech and better speaker labels
  • Soniox moves to v5 for higher accuracy across 60+ languages, better speaker separation, and cleaner handling of numbers, dates, and emails
  • Gladia Solaria-3 for English, French, German, Spanish, and Italian recordings
  • Speechmatics Melia-1 detects and switches between 56+ languages automatically, with no language selection needed
  • OpenAI GPT-4o Transcribe Diarize returns speaker-labeled transcripts, and full-size Whisper Large V3 is now selectable on Groq

Latest AI Models

  • Claude Sonnet 5, the GPT-5.6 family, Grok 4.5, GLM-5.2, and Gemini 3.6 Flash join the lineup
  • GPT-5.6 models are available on the OpenAI sign-in path too, so you get them without an API key
  • Kimi now defaults to K3 and Cerebras to GPT-OSS 120B
  • Retired models are upgraded to their replacements automatically - no mode breaks, no re-picking needed

Quality of Life

  • The keyboard session timeout gained a "Never" option, and changes now apply to the running session right away
  • Hot mic sessions gained an in-app stop control
  • When adding your own OpenAI-compatible transcription server you can now choose how audio is sent, so endpoints that only accept it inside a JSON request finally work