transcribe-heTranscribe audio or video files using the TextOps/Modal API. Use this skill whenever the user wants to transcribe a video or audio file, mentions an mp4/mp3/...
Install via ClawdBot CLI:
clawdbot install netanelrotem/transcribe-heGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → https://us-central1-whisper-cloud-functions.cloudfunctions.net/check_modal_jobCalls external URL not in known-safe list
https://text-ops-subs.com/api/keysAudited Apr 17, 2026 · audit v1.0
Generated May 3, 2026
Transcribe interviews, podcasts, or recorded meetings for producing accurate written records or subtitles. The skill handles Hebrew and multilingual audio, with optional speaker diarization for multi-speaker content.
Convert court hearings, depositions, or client consultations into text for case documentation, evidence review, or regulatory compliance. Word-level timestamps can be enabled for precise references.
Transcribe lectures, focus groups, or field interviews for qualitative analysis. Researchers can process audio in Hebrew and other languages, with speaker identification to separate participants.
Generate text records of doctor-patient conversations for electronic health records (EHR) or telemedicine documentation. Supports secure local file processing and URL-based transcription.
Automate the creation of meeting minutes from recorded audio/video files. The skill provides downloadable JSON and plain text transcripts, with progress updates during processing.
Charge per audio duration or file processed, with tiered pricing based on features like speaker diarization or word timestamps. Customers use their own TEXTOPS_API_KEY, enabling usage-based billing.
Offer monthly or yearly plans with a set number of transcription minutes, appealing to media companies, legal firms, or research institutions with regular transcription needs.
License the transcription skill to SaaS platforms (e.g., project management tools, note-taking apps) for embedding in their workflows. Revenue from per-seat licensing or revenue share.
💬 Integration Tip
To integrate, ensure the TEXTOPS_API_KEY environment variable is set and install optional ffprobe for time estimates. The script accepts both local file paths and URLs, and can be called via command line or programmatically.
Scored Apr 19, 2026
Local speech-to-text with the Whisper CLI (no API key).
ElevenLabs text-to-speech with mac-style say UX.
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
Text-to-speech conversion using node-edge-tts npm package for generating audio from text. Supports multiple voices, languages, speed adjustment, pitch control, and subtitle generation. Use when: (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, driving, cooking). (3) User wants a specific voice, speed, pitch, or format for TTS output.
Local text-to-speech via sherpa-onnx (offline, no cloud)
Start voice calls via the OpenClaw voice-call plugin.