Transcribe File(s)¶
What This Feature Does¶
Transcribe File(s)... provides queue-based transcription for existing audio/video files and writes per-file output session folders.
Design Rationale¶
Existing-file workflows prioritize throughput and repeatability:
- queue multiple files/folders
- monitor per-item status
- generate consistent output artifacts
- optionally apply LLM post-processing without changing source transcript
Queue and Status Model¶
| Status | Meaning |
|---|---|
| Queued | Waiting to process |
| In progress | Currently transcribing |
| Completed | Finished with outputs available |
| Failed | Processing error recorded |
Input Handling¶
- Supports drag-and-drop and
Add Files.../Add Folder.... - Folder input is expanded to supported media files.
- Duplicate paths are de-duplicated in queue assembly.
Output Artifacts Per Item¶
Per input item, outputs can include:
transcript.txttranscript.words.jsonltranscript.srttranscript.vtttranscript.ttmltranscript.smpte-tt.ttmltranscript.llm.txttranscript.llm-request.json
Choosing Output Formats¶
Use TXT for a readable transcript, SRT for broadly supported subtitles, and WebVTT for web players. TTML and SMPTE-TT are mainly for professional delivery requirements, while word timing JSONL is intended for custom tooling and detailed timing analysis.
The LLM output is a transformed companion to the original transcript, not a replacement for it. See Output Formats Explained for definitions and recommended bundles.
Settings Reference¶
| Setting | Notes |
|---|---|
| Output directory | Root for per-item session folders |
| Chunking | Controls transcript segmentation behavior, not audio recapture |
| Chunk (s) | Segmentation interval for long-form readability |
| Subtitle cue split mode | Affects subtitle pacing/structure |
| LLM post-processor | Reusable provider, endpoint, model, prompt, timeout, credential, and wrapping configuration |
| LLM Post-Processor Output | Sends each completed file transcript to the selected post-processor and writes transcript.llm.txt without changing the original transcript |
| Save LLM Request Payload | Optionally saves the exact request body, which can contain transcript and rendered prompt content |
Segmentation Principle¶
When chunking is enabled, the system segments transcript output for readability and subtitle utility. It does not re-record source media or change original audio fidelity.
LLM Post-Processing Path¶
If enabled:
- Base transcript is produced first.
- The selected library processor supplies its prompt, provider configuration, and optional wrapping tags.
- LLM processes the transcript.
.llm.txtand optional.llm-request.jsonare written.
Choose the processor from the LLM Post-Processor menu. Edit Processor... opens that exact entry in the shared library, and Test LLM Post-Processing... stays live as the selection or processor settings change.
Editing a processor also affects any profile or Meeting workflow intentionally using the same entry. Duplicate it first when file batches need independent behavior.
Transformation Examples¶
Example 1: Base Transcript Output¶
Input media spoken content:
today we reviewed launch blockers and assigned action items
transcript.txt output:
today we reviewed launch blockers and assigned action items
Example 2: LLM-Processed Variant¶
Same base transcript with LLM enabled:
transcript.llm.txt output:
Today we reviewed launch blockers and assigned action items.
What changed:
- punctuation and capitalization improved
- meaning stayed the same
Recommended Baselines¶
| Use Case | Chunking | LLM | Formats |
|---|---|---|---|
| Fast archive | On | Off | TXT |
| Review/edit workflow | On | Off | TXT + SRT/VTT |
| Analysis workflow | On | On | TXT + SRT/VTT + LLM outputs |
Common Pitfalls¶
| Pitfall | Symptom | Fix |
|---|---|---|
| Huge queue + heavy LLM | Long completion times | Run base transcript pass first, LLM second |
| Output mismatch expectations | Missing files | Confirm toggles before run |
| Confusing chunking behavior | Unexpected segment boundaries | Adjust chunk seconds and cue split settings |
| Unexpected shared LLM behavior | Another workflow changes after editing the processor | Select or duplicate a separate processor for file transcription |
Validation Checklist¶
- Queue contains expected files only.
- Status transitions complete without unexpected failures.
- Output directory per item is created and populated.
- LLM outputs exist only when enabled.
In-App Help Cues For This Feature¶
In Transcribe File(s)..., use ? help beside:
- transcript/subtitle output toggles
- reusable LLM processor selection and output behavior
- cue split options
- chunking semantics
Quick Tips¶
- File transcription always preserves the source media. Chunking changes transcript segmentation, not the original audio or video.
- The LLM result is a companion artifact. Keep
transcript.txtenabled so you can compare a model rewrite with the recognized source.
See Also¶
- Long-Form Recording
- Profiles
- LLM Post-Processing Guide
- Output Formats Explained
- Transcribe Audio and Video Files
- Troubleshooting
- In-App Help Cues (? Buttons and Hover Tooltips)
- Glossary
Visual Notes¶
- TODO: add screenshot of queue list and status chips.
- TODO: add screenshot of file transcription settings panel.
- TODO: add GIF adding a folder and processing multiple files.