Implement speech-to-text transcription workflow with Deepgram. Use when building pre-recorded audio transcription, batch processing, or implementing core transcription features. Trigger with phrases like "deepgram transcription", "speech to text", "transcribe audio", "audio transcription workflow", "batch transcription".
7.0
Rating
0
Installs
AI & LLM
Category
This skill provides a comprehensive, production-ready implementation of Deepgram's pre-recorded transcription workflow. The description clearly indicates when to use this skill (batch transcription, speech-to-text workflows) and appropriate trigger phrases. Task knowledge is excellent with complete TypeScript and Python service classes, batch processing, error handling tables, and speaker diarization examples. The structure is logical and well-organized with clear sections, though it could benefit from separating large code examples into referenced files for easier maintenance. Novelty is solid: implementing a full transcription service with proper error handling, batch processing, and multiple language support saves significant development time and API exploration that would otherwise require many LLM tokens. Minor deductions for: (1) structure could be more modular with separate files for large examples, (2) novelty is good but not exceptional as the API wrapper patterns are relatively straightforward once documented. Overall, this is a high-quality, immediately actionable skill that would meaningfully benefit a CLI agent.
jeremylongshore
Skill Author
Loading SKILL.md…
