Skip to content

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.