Skip to content

2026

  • 1 min read

1.12.1

Dopdock Release Notes

Speech-to-text download stability

  • Added support for downloading the Whisper Large v3 on-device speech-to-text model.
  • Improved reliability when speech-to-text model downloads fail.
  • Replaced unclear error messages with helpful, readable guidance so failures no longer cause the app to crash.
  • Improved error handling for local app storage problems.

The existing Whisper Large v3 download source remains unchanged.

  • 1 min read

1.12.0

Text to Speech action

You can now add a Text to Speech step to any command. It reads text out loud using ElevenLabs' voices and waits for playback to finish before moving on to your next step — perfect for having Dopdock read back a summary, a translation, or any generated text.

  • Pick from your ElevenLabs voices, or enter a custom voice ID.
  • Dopdock automatically uses the right voice model for you — no extra configuration needed.
  • Optionally insert your selected text, clipboard contents, the current date, or the current time into what gets spoken.
  • Set how many times the audio should play.

New dictation models from ElevenLabs

Two new cloud transcription models, ElevenLabs Scribe v1 and Scribe v2, are now available as dictation options alongside the existing providers.

Settings

Added an ElevenLabs card in Settings where you can add your API key to enable both the new Text to Speech action and the new Scribe dictation models.

  • 1 min read

1.11.1

This release makes voice-driven workflows faster, more reliable, and easier to set up.

Highlights

  • New Whisper Large v3 Turbo model: Download and use a faster local transcription model that delivers nearly the accuracy of Whisper Large while using about 1.5 GB of memory.
  • Continuous listening timeout: Set how long monitor-based voice commands should remain active without a matched command, from 1 to 60 minutes. Recognized commands automatically restart the timer.

Improvements

  • More resilient voice monitoring: A temporary speech-recognition error no longer ends continuous listening. Dopdock keeps monitoring for the next command and safely recovers if the audio stream stops unexpectedly.
  • Better long-audio handling: Overly long ambient-audio chunks are skipped so they do not delay recognition of short voice commands.
  • Smoother accessibility setup: The onboarding screen now detects permission changes automatically after you grant access in System Settings.

Fixes

  • Window focus: Switching Dopdock between background and foreground window modes no longer unexpectedly steals focus from the app you are using.
  • 1 min read

1.11.0

This release makes voice-driven workflows faster, more reliable, and easier to set up.

Highlights

  • New Whisper Large v3 Turbo model: Download and use a faster local transcription model that delivers nearly the accuracy of Whisper Large while using about 1.5 GB of memory.
  • Continuous listening timeout: Set how long monitor-based voice commands should remain active without a matched command, from 1 to 60 minutes. Recognized commands automatically restart the timer.

Improvements

  • More resilient voice monitoring: A temporary speech-recognition error no longer ends continuous listening. Dopdock keeps monitoring for the next command and safely recovers if the audio stream stops unexpectedly.
  • Better long-audio handling: Overly long ambient-audio chunks are skipped so they do not delay recognition of short voice commands.
  • Smoother accessibility setup: The onboarding screen now detects permission changes automatically after you grant access in System Settings.

Fixes

  • Window focus: Switching Dopdock between background and foreground window modes no longer unexpectedly steals focus from the app you are using.
  • 1 min read

1.10.2

  • Start a new dictation while an earlier one is still being processed, so your ideas keep flowing without waiting.
  • Keep dictation results in the order you recorded them, even when some take longer to process.
  • Get clearer status-bar controls while dictations are queued.
  • Improved compatibility and reliability with the Speechall transcription service.
  • 1 min read

1.10.1

  • Updated the Speechall Swift SDK to the latest pinned revision.
  • Improved compatibility with Speechall’s updated model-listing API and transcription schemas.
  • Speechall model IDs are now handled dynamically, supporting newly available models without requiring an app update.
  • 1 min read

1.9.5

  • Added experimental Speechall streaming transcription for faster dictation results while recording.
  • Kept Speechall streaming off by default and added an Experimental Features setting to enable it.
  • Improved recovery when a streaming transcription request fails so dictation can be started again without restarting Dopdock.
  • Improved local purchased-mode development launch logging.
  • 1 min read

1.8.2

  • Added Markdown mode for Paste Rich Text actions, including a plain-text Markdown editor and backward-compatible rich text actions
  • Improved rich Markdown paste behavior for Slack and other editors by adding HTML, RTF, and plain-text pasteboard formats
  • Improved Markdown code rendering for inline code and fenced code blocks
  • Added a debug Markdown paste action to make rich paste behavior easier to test
  • Added a local debug purchased launch script for testing purchased app behavior