deepgram-transcribeTranscribe audio via Deepgram Nova-3 API (5.26% WER, 40x faster than Whisper, built-in speaker diarization). Use when user asks to transcribe audio, podcasts...
Install via ClawdBot CLI:
clawdbot install jessewunderlich/deepgram-transcribeGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → https://api.deepgram.com/v1/listen?${PARAMS}Calls external URL not in known-safe list
https://api.deepgram.com/v1/listen?${PARAMS}AI Analysis
The skill's external API call to Deepgram is fully consistent with its documented purpose of audio transcription, and the endpoint is a legitimate, well-known service. The primary risk is the standard data privacy consideration of sending user audio to a third-party API, not unauthorized exfiltration or hidden malicious behavior.
Audited Apr 17, 2026 · audit v1.0
Generated Mar 20, 2026
Transcribe podcast episodes for editing, SEO optimization, and creating show notes. The speaker diarization feature helps identify hosts and guests, streamlining content repurposing.
Record and transcribe business meetings to generate accurate minutes and action items. The fast processing enables real-time or post-meeting summaries for team collaboration.
Transcribe interviews, lectures, or focus groups for qualitative analysis. The low word error rate ensures reliable data extraction for studies and publications.
Transcribe call recordings to analyze customer interactions, identify trends, and improve service quality. Supports multiple audio formats from various recording systems.
Transcribe legal depositions and hearings with high accuracy for documentation and evidence. The smart formatting aids in creating clear, punctuated transcripts for case files.
Offer transcription as a service with tiered pricing based on usage (e.g., minutes per month). Target small businesses and freelancers needing regular audio processing.
Integrate the skill into a larger platform (e.g., project management tools) and charge per transcription request. Leverage Deepgram's free credits to minimize initial costs.
Provide custom integration services for enterprises needing transcription in workflows like CRM or compliance systems. Charge for setup, training, and ongoing support.
💬 Integration Tip
Set the DEEPGRAM_API_KEY environment variable or use the fallback to OpenAI Whisper for seamless operation without API key issues.
Scored Apr 19, 2026
Local speech-to-text with the Whisper CLI (no API key).
Local speech-to-text using OpenAI Whisper. Runs fully offline after model download. High quality transcription with multiple model sizes.
Text-to-speech via OpenAI Audio Speech API.
Generate spoken audio from text using the local Kokoro TTS engine. Use when the user asks to "say" something, requests a voice message, or wants text converted to speech.
Convert text to speech using Hume AI (or OpenAI) API. Use when the user asks for an audio message, a voice reply, or to hear something "of vive voix".
Speech-To-Text with MLX (Apple Silicon) and opensource models (default GLM-ASR-Nano-2512) locally.