nexus-voice-transcriberVoice note transcription and archival for OpenClaw agents. Powered by Deepgram Nova-3 or local Whisper. Transcribes audio messages, saves both audio files an...
Install via ClawdBot CLI:
clawdbot install matthew00ita/nexus-voice-transcriberGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://clawhub.ai/skills/voice-transcriberAudited May 10, 2026 · audit v1.0
Generated Oct 6, 2026
Law firms use the skill to transcribe lengthy deposition recordings for case preparation. Local Whisper handles sensitive client audio without sending it to external APIs, while Deepgram diarization identifies multiple speakers (attorney, witness, judge) for accurate attribution.
Podcasters submit interview audio to generate transcripts for show notes, website SEO, and accessibility. They use SRT output to create accurate captions for YouTube and social media, with Deepgram's speaker labels simplifying guest-host differentiation.
Healthcare providers record patient encounters and need quick, secure transcription for electronic health records. Local Whisper ensures HIPAA-friendly on-device processing, avoiding transmission of protected health information to third-party APIs.
Researchers transcribe qualitative interviews and focus groups, often in multiple languages. The skill's chunking of long audio, JSON output with timestamps, and local processing for sensitive topics make it ideal for field studies where internet may be unreliable.
Businesses transcribe recorded support calls to analyze sentiment, compliance, and agent performance. Deepgram with diarization separates agent and customer speech, while archived audio and transcripts provide a searchable knowledge base.
A cloud-based platform that wraps the skill to offer unlimited voice note transcription with tiered plans for individuals and teams. Users upload audio via a web dashboard, and the service handles provider selection, chunking, and storage.
Sell a self-hosted version of the voice transcriber to enterprises in healthcare, legal, or finance that require strict data privacy. The package includes setup scripts, model management, and integration with internal storage and authentication systems.
Offer a developer-friendly REST API that abstracts provider selection (Whisper vs. Deepgram) and handles audio preprocessing, chunking, and format conversion. Developers pay per minute of audio processed, with volume discounts.
💬 Integration Tip
Start with local Whisper for zero-cost, privacy-safe transcription, then add Deepgram only when diarization or higher accuracy is needed; ensure ffmpeg is installed and use the provided script for automatic chunking of long files.
Scored May 10, 2026
Transcribe audio files with speaker diarization (who speaks when). Supports 100+ languages, automatic language detection, and timestamps. Use for meetings, interviews, podcasts, or voice messages. Requires AssemblyAI API key.
使用 poocr 库识别发票并导出 Excel。当用户需要识别增值税发票、批量处理发票文件或提取发票信息到 Excel 时调用此技能。
Use when the user has audio or video and wants a timestamped transcript (SRT) in the source language. Routes by source language — Chinese defaults to Volcano...
Create, manage, and deploy ElevenLabs conversational AI agents. Use when the user wants to work with voice agents, list their agents, create new ones, or manage agent configurations.
Voice note transcription and archival for OpenClaw agents. Powered by Deepgram Nova-3. Transcribes audio messages, saves both audio files and text transcript...
Text-to-Speech (TTS) and Speech-to-Text (ASR) using coze-coding-dev-sdk. Returns results directly to stdout.