transcribe-clips
Use when transcribing raw footage clips using Deepgram. Produces timestamped JSON per clip with word-level timing and optional speaker diarization for multi-speaker content.
| Model | Source |
|---|---|
| sonnet | pack: video-pipeline |
Full Reference
transcribe-clips
Section titled “transcribe-clips”Transcribes all usable clips from clip-manifest.json using Deepgram’s Nova-2 model. Produces per-clip timestamped JSON with word-level timing, paragraph segmentation, and utterance boundaries. Supports speaker diarization for interviews and multi-speaker content. Skipped clips never halt the pipeline. Outputs to transcripts/ directory.
Quick Reference
Section titled “Quick Reference”| Item | Value |
|---|---|
| API dependency | DEEPGRAM_API_KEY env var |
| Model | Deepgram Nova-2 |
| Input | clip-manifest.json in current directory |
| Output | transcripts/<clip-name>.json per clip |
| Next stage | classify-and-plan-edit |
| Rate limit handling | Backoff 60s, retry 3× |
Reference Index
Section titled “Reference Index”| I want to… | File |
|---|---|
| Set up API key, configure Deepgram params, run transcription, handle errors | reference/setup.md |
| See the per-clip JSON schema and progress summary format | reference/output.md |
Usage: Read the reference file matching your current task from the index above. Each file is self-contained with code examples and inline gotchas.
Announcement
Section titled “Announcement”┏━ ⚡ transcribe-clips ━━━━━━━━━━━━━━━━━━━━━━━━━━━┓ ┃ Transcribing [count] clips via Deepgram ┃ ┗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┛