mh-openai-whisperLocal speech-to-text with the Whisper CLI (no API key).
Install via ClawdBot CLI:
clawdbot install mohdalhashemi98-hue/mh-openai-whisperGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://openai.com/research/whisperAudited Apr 17, 2026 · audit v1.0
Generated Mar 20, 2026
Local transcription of podcast episodes for content creators, enabling quick generation of show notes or subtitles without relying on cloud services. Useful for editing and accessibility compliance.
Transcribing recorded business meetings to create accurate minutes, saving time on manual note-taking. Helps teams review discussions and track action items efficiently.
Adding captions to lecture recordings or educational videos to enhance accessibility for students. Supports learning environments by making content more inclusive and searchable.
Transcribing interviews for journalists to quickly extract quotes and key insights, streamlining the writing process. Reduces dependency on external transcription services.
Automatically transcribing customer support calls for quality assurance and training purposes. Enables analysis of common issues and improves service efficiency.
Offer basic local transcription for free with limited features, then charge for advanced models, batch processing, or integration with other tools. Targets small businesses and individual creators.
Sell licenses to corporations for internal use, such as transcribing meetings or training materials. Includes support, customization, and compliance features for large-scale deployment.
Provide an API that wraps the Whisper CLI for developers to integrate speech-to-text into their applications. Monetize based on usage volume or through premium support packages.
💬 Integration Tip
Ensure the Whisper CLI is installed via brew and test with sample audio files first to verify model downloads and output formats.
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.