asrFast, affordable automatic speech-to-text transcription supporting 100 languages, speaker diarization, word timestamps, and customizable output formats.
Install via ClawdBot CLI:
clawdbot install ilyakam/asrGrade Good — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
webhook → https://mysite.com/callbackCalls external URL not in known-safe list
https://speechischeap.comAI Analysis
The skill's external API calls (speechischeap.com, upload.speechischeap.com) are consistent with its stated purpose of speech-to-text transcription, and the webhook feature is user-configured rather than a hidden data exfiltration channel. However, it sends audio data to a third-party service not on a known-safe list, which introduces a standard privacy risk for any cloud-based transcription tool.
Audited Apr 16, 2026 · audit v1.0
Generated Mar 20, 2026
Automatically transcribe podcast episodes for show notes, SEO, and accessibility. The fast processing and multilingual support allow creators to quickly generate transcripts for global audiences.
Transcribe customer service calls to analyze sentiment, identify common issues, and improve training. The low cost enables high-volume processing of calls across multiple languages.
Transcribe interviews and focus groups for qualitative analysis. The speaker diarization and word-level timestamps help researchers accurately attribute quotes and analyze dialogue patterns.
Transcribe court proceedings, depositions, and client meetings for accurate record-keeping. The privacy mode ensures sensitive audio is not stored, complying with confidentiality requirements.
Transcribe video or audio content in one language and use the output for translation and subtitling. The support for 100 languages streamlines the creation of multilingual content.
Offer a free tier with limited transcription hours to attract users, then charge based on usage volume. The disruptive pricing allows competitive subscription plans for small to large enterprises.
License the transcription technology to other platforms, such as video hosting sites or CRM tools, integrating it as a built-in feature. This leverages the agent-ready design for seamless automation.
Provide custom integrations for large organizations needing high-volume transcription, such as call centers or media companies. Offer advanced features like webhooks and private mode for tailored workflows.
💬 Integration Tip
Set the SIC_API_KEY environment variable in your agent config to avoid authentication errors, and use the JSON output for easy parsing in automated pipelines.
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.