Transcribe audio files with speaker diarization and word-level timestamps via ElevenLabs Scribe v2.
npx skills add https://github.com/syahravi/openclaw --skill elevenlabs-stt
Please help me install this Agent Skill. Skill: elevenlabs-stt Source: https://github.com/syahravi/openclaw/tree/main/elevenlabs-skill Command: npx skills add https://github.com/syahravi/openclaw --skill elevenlabs-stt
Convert audio and video recordings into accurate, searchable text while optionally identifying speakers and audio events to save manual transcription time.
Transcribe the attached audio file meeting.mp3 with speaker diarization enabled and return the full JSON output with word-level timestamps.
High-intent search queries and answers about installing and using this skill.
Speech-to-text transcription supports 90+ languages and includes automatic language detection for global audio sources. You can transcribe multi-speaker meetings, podcasts, and voice notes across diverse languages without manual language specification.
Speech-to-text transcription accepts common audio and video formats as input. You can process media files directly without needing separate audio extraction, receiving plain text or detailed JSON with timestamps as output.
Audio event tagging during transcription can detect non-speech sounds like laughter, music, and applause. This enriches the transcript output and aids editing workflows by identifying specific audio events alongside the transcribed text.
To authenticate speech-to-text requests using ElevenLabs Scribe v2, you need an API key. You must also ensure your environment includes curl and jq dependencies to execute the transcription scripts and parse the JSON output.
kcns008Transcribe audio files into text via the OpenAI Whisper API.
barefootfordTranscribes video audio into timestamped JSON transcripts with word-level timing using WhisperX.
EstomTranscribe audio files into text with optional speaker diarization.
QcasaresTranscribe audio to text using ElevenLabs' Scribe v2 API.