Audio transcription and summarization

Transcribe segments concurrently, restore chronology, and produce a traceable summary.

ingest audio→segment→transcribe segment 1transcribe segment N→merge transcript→summarize→publish

Audio transcription and summarization

Activity responsibilities

Activity	Responsibility
ingest-audio	Execute the ingest audio stage and publish its declared outputs for downstream activities.
segment	Execute the segment stage and publish its declared outputs for downstream activities.
transcribe-segment-1	Execute the transcribe segment 1 stage and publish its declared outputs for downstream activities.
transcribe-segment-n	Execute the transcribe segment N stage and publish its declared outputs for downstream activities.
merge-transcript	Execute the merge transcript stage and publish its declared outputs for downstream activities.
summarize	Execute the summarize stage and publish its declared outputs for downstream activities.
publish	Execute the publish stage and publish its declared outputs for downstream activities.

Inputs

• Audio
• Language settings
• Model versions

Outputs

• Segment text
• Transcript
• Summary

Provenance to preserve

• Segment timestamps
• Confidence
• Summary prompt

Runnable example

This is the complete checked-in bundle for this pattern. Download the environment, scope, topology, workflow, input, container recipe, runner, and validation contract from this page before executing it.

Read setup instructions ↓Environment YAML ↓Execution scope YAML ↓Network topology YAML ↓Workflow YAML ↓Input data ↓Container recipe ↓Run the workflow ↓Validate outputs ↓Expected output manifest ↓

Verified local execution

These captures and the output manifest were produced by the fixture's local Docker run and validator. They are published with the same bundle as the runnable files.

Workflow evidence

Execution evidence

Output evidence

Open verified output manifest ↓

Execution considerations

Overlap segment boundaries where needed and reconcile speaker identity during merge. Different stages may target GPU and CPU resources.

AkôFlow boundary: the engine schedules, deploys, executes, transfers data, and records evidence. The ML or agent framework remains an implementation choice inside each activity.