# Video Transcription Q&A

Transcribe speech in videos and build a knowledge base index for retrieving training or explanatory video content.

## Prepare your resources

Prepare a training video, a knowledge base, and an output volume. Use familiar content to check names, numbers, and key statements.

This template prepares searchable transcripts; Q&A takes place afterward. It processes speech, not individual video frames, and does not infer content from silent scenes.

## Use the template

On the workflow creation page, start from a template, search for **Video Transcription Q&A**, and load it onto the canvas.

Complete the required fields in the parameter form.

| Setting | Purpose |
| --- | --- |
| Input video | Video files or a volume containing them |
| Target knowledge base | Select an existing knowledge base or create one |
| Catalog save location | Location for the ZIP archive of chunked transcripts |

Save the parameters, then start a manual run. The system saves the current workflow before submitting execution.

## Complete processing flow

Arrows show execution order; configured bindings supply each step’s input.

![Video Transcription Q&A](../images/video-knowledge-base-flow.svg)

## Configure transcription and chunking

| Setting | Default and use |
| --- | --- |
| Input video | Select files or a volume and confirm scope |
| Language | `auto`; choose `zh` or `en` when the main language is known |
| Noise reduction | `auto`; alternatives are `off` and `ffmpeg_afftdn`; compare on a noisy sample |
| Chunk size | 512 characters |
| Overlap | 50; at least 0 and less than chunk size |
| Three-level index | Enabled, section size 5 |
| Knowledge base and destination | Receive indexes and transcript files respectively |

Chunk settings apply to text, not video duration. Larger chunks do not repair transcription errors; verify transcription before adjusting retrieval context.

## Check transcripts, indexes, and files

1. Confirm selected files and counts.
2. Compare parser `documents` and nonempty `text` with the original, checking names, numbers, and complete statements.
3. Inspect chunk context and source metadata.
4. Check index writes; three-level row counts differ from file counts.
5. Open the transcript ZIP at the destination and inspect records and source relationships.
6. Test retrieval using a question answered in the training video.

The template writes **chunked transcript documents** to ZIP, saves that file, and registers sources. This differs from the document knowledge base template, which saves records before chunking.

## Example: organize a training video

Select a training video, keep automatic language detection and default chunking, choose destinations, and run. Compare a key passage with its transcript, then retrieve the same topic. Adjust overlap or chunk size only after confirming transcription accuracy.

## Common problems

| Symptom | Check and action |
| --- | --- |
| Names or numbers are incorrect | Compare with speech and check language and noise |
| No text is returned | Check for recognizable speech and inspect parser output |
| Retrieved context is incomplete | Verify the transcript, then inspect chunks and overlap |
| Indexing succeeds but saving fails | Inspect later writing/saving status before repeating existing writes |
| Only one file is visible for multiple sources | Inspect all `file_ids` from document writing, not only the primary `file_id` |

## Related pages

- [Workflow templates](index.md)
- [Run and debug](../run-debug.md)