whisper-transcriberOffline speech-to-text (ASR) using whisper.cpp (whisper-cli) + ffmpeg. Supports batch transcription, timestamps, SRT/TXT/JSON outputs, and model download. Cr...
Install via ClawdBot CLI:
clawdbot install vvusu/whisper-transcriberGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/ggml-org/whisper.cppAudited Apr 17, 2026 · audit v1.0
Generated Mar 20, 2026
Universities and educational institutions can use this offline tool to transcribe recorded lectures and seminars. The batch processing capability allows handling multiple recordings from different courses efficiently, while SRT output supports creating subtitles for accessibility.
Journalists and media professionals can transcribe field interviews and press conferences offline, ensuring privacy and security for sensitive content. The timestamp feature helps locate specific quotes, and JSON output enables easy integration with content management systems.
Healthcare providers can transcribe patient consultations for medical records while maintaining data privacy through offline processing. The Chinese language support is valuable in regions where it's the primary language, and the tool works without internet connectivity in clinical environments.
Law firms and court systems can transcribe depositions, hearings, and client meetings with reliable offline operation. The ability to process multiple files in batch saves time for paralegals, and the tool's cross-platform nature supports different office IT environments.
Businesses can automatically transcribe internal meetings, board discussions, and training sessions. The offline capability ensures corporate data never leaves the premises, while configurable language settings support multinational organizations with diverse language requirements.
Offer a managed version with premium support, custom model training, and integration services for large organizations. Provide regular updates, security patches, and compliance documentation for regulated industries like healthcare and legal services.
Provide professional services to help organizations implement the transcription solution within their existing workflows. Offer customization for specific industry needs, training for staff, and development of custom scripts for automation pipelines.
Create specialized packages for schools, universities, and research institutions with academic pricing. Include bulk licensing for computer labs, integration with learning management systems, and specialized support for research projects requiring transcription.
💬 Integration Tip
The skill requires ffmpeg and whisper-cli binaries, so ensure these dependencies are properly installed and accessible in the system PATH before attempting integration.
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.