// SKILLTranscription

AssemblyAI Transcriber

Convert voice messages, audio files, and recordings to accurate text. Powered by AssemblyAI's speech-to-text engine with speaker diarization.

/assemblyai-transcriber

KEY FEATURES

1

Transcribe Telegram voice messages automatically

2

Support for audio files (MP3, WAV, M4A, OGG)

3

Speaker diarization (identify who's speaking)

4

Punctuation and paragraph detection

5

Support for 99+ languages

CONFIGURATION EXAMPLE

openclaw.json
"skills": {
  "entries": {
    "assemblyai-transcriber": { "enabled": true }
  }
}

EXAMPLE CONVERSATION

U

[Voice message: 45 seconds]

B

Transcription complete: "Hey team, I wanted to follow up on yesterday's meeting. The client approved the design mockups and wants us to proceed with development. The deadline is still March 15th. Let me know if you need any clarification." - Duration: 0:45 - Language: English - Confidence: 97%

TIPS & BEST PRACTICES

Works best with clear audio — background noise reduces accuracy

Long audio files are processed in chunks (may take a few seconds)

Pair with TubeScribe for a complete media processing pipeline

RELATED SKILLS

Enable on your bot

AssemblyAI Transcriber · Transcription

DASHBOARD