Back to all skills
๐ŸŽ™๏ธ
Communication

Voice Assistant

Dictate, transcribe, and generate voice replies with cloned or stock voices.

4.6rating
2,600 installs
voice-io + elevenlabs-bridge
Max required

About this skill

Voice Assistant records your dictation, transcribes it with punctuation and speaker labels, and can read back generated replies with a stock voice or a voice clone you've enrolled. Useful for walking meetings, voice memos you want turned into emails, or accessibility workflows. Works offline for transcription; voice generation requires an API key for your preferred TTS provider.

What it does

  • Local transcription with speaker diarization
  • Voice cloning with your own enrolled sample
  • TTS with stock voices or provider bridge
  • Walking-meeting mode (noise-robust)
  • Export transcripts as email, doc, or notes

Use cases

  • Turn a 20-minute walking memo into a structured email
  • Transcribe a client call with speaker labels
  • Generate a voice reply in your own cloned voice