transcription-speech-to-text-hebrewTranscribe 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/transcription-speech-to-text-hebrewGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → https://agents.text-ops-subs.com/api/v2/transcribe-statusCalls external URL not in known-safe list
https://agents.text-ops-subs.comAI Analysis
The skill sends audio/video data to a documented external API (agents.text-ops-subs.com) for transcription, which is consistent with its stated purpose. While the data sink is external, it is disclosed in the skill's privacy section, and the API key requirement is transparent. No hidden instructions, credential harvesting, or obfuscation were detected.
Audited Apr 16, 2026 · audit v1.0
Generated May 3, 2026
A university professor records lectures in Hebrew and uses this skill to automatically transcribe them into text, including speaker diarization to distinguish between the lecturer and student questions. The skill processes mp4 files and outputs timestamped transcripts for student review.
A market research firm conducts customer interviews in Hebrew and English, recorded as audio files. Using this skill, they transcribe the interviews with word-level timestamps and speaker diarization to analyze responses and identify trends efficiently.
A content creator downloads their own Hebrew YouTube videos using the built-in YouTube download feature, then transcribes the audio to generate text for blog posts, show notes, and social media captions. The skill automatically handles the download and transcription workflow.
A law firm receives court hearing recordings in Hebrew (mp3 format) and needs accurate text transcripts with speaker identification. The skill transcribes the files, and the firm uses the output for case preparation and legal documentation.
Users pay per audio minute or per transcription job via API credits purchased through TextOps. The skill integrates directly with the TextOps API, which bills based on usage. Revenue comes from per-transaction fees.
Provide a limited number of free transcriptions per month (e.g., 10 minutes) to attract users, then charge for additional minutes or premium features like word-level timestamps and higher speaker limits. Revenue from subscription or one-time purchases.
Offer the transcription capability as a white-label service integrated into enterprise platforms (e.g., LMS, CRM). Enterprises pay a flat licensing fee or per-seat subscription, and the skill is customized with their branding.
💬 Integration Tip
Set the TEXTOPS_API_KEY environment variable and ensure Python 3.8+ is available. The skill auto-detects file types and handles YouTube downloads, so minimal user setup is needed.
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.