MEDIA ENGINEERING / Agency Agents community
Speech transcript pipeline designer
A speech-pipeline reference covering audio validation, chunked ASR, speaker assignment and structured output.
“Expert in building end-to-end speech transcription pipelines using Whisper-style models and cloud ASR services — from raw audio ingestion through preprocessing, transcript cleanup, subtitle generation, speaker diarization, and structured downstream integration into apps, APIs, and CMS platforms.”
01 / THE REASONING
Why this made the selection.
- It preserves timestamps and low-confidence review flags rather than silently deleting uncertain speech.
- The sample speaker assignment uses maximum time overlap, while chunk assembly offsets segments back onto the original timeline.
02 / THE REVIEW RECORD
What we actually inspected.
Source review has boundaries.
A clear record is more useful than a “safe” badge.
Material inspected
- engineering/engineering-voice-ai-integration-engineer.md (pinned complete source retained)
- LICENSE
- Repository README and current official host configuration documentation
Our findings
- It preserves timestamps and low-confidence review flags rather than silently deleting uncertain speech.
- The sample speaker assignment uses maximum time overlap, while chunk assembly offsets segments back onto the original timeline.
Not established by this review
- Source review only: no agent was installed or invoked. Task correctness, effective host restrictions and integration behaviour were not tested.
The review applies to the material and revision named here. A newer upstream release can change its behavior.
03 / PUT IT TO WORK
Use the role in your project.
- Read the pinned source and its licence, then configure an explicitly bounded host context.
- Check the original display-style name and optional color/emoji/vibe metadata against the installed host requirements before loading a working copy. Current Claude Code documentation says unknown frontmatter fields are ignored; it does not establish a need to rewrite these names. Keep the archived/downloaded original unchanged.
- Treat the code as an adaptation reference: pin ASR/diarization dependencies, resolve gated-model terms, test boundary alignment against original audio and choose data handling from the actual requirements.
- Supply authorized audio, language, retention constraints and output timing/speaker requirements.
Before you start
- ffmpeg/ffprobe and compatible Python ASR stack
- Diarization model access if used
- Authorized audio and measured transcript QA
04 / FOLLOW THE EVIDENCE
The source trail.
Our notes are separate from the original resource.
Check upstream before adopting a new version.
https://github.com/msitarzewski/agency-agents/blob/bd956db032d907387e6b9ddebff3e18f1de8c679/engineering/engineering-voice-ai-integration-engineer.md
Supports: Workflow, inputs, outputs and stated boundaries
- Applicable licence ↗Checked
https://github.com/msitarzewski/agency-agents/blob/bd956db032d907387e6b9ddebff3e18f1de8c679/LICENSE
Supports: Redistribution and attribution
https://code.claude.com/docs/en/sub-agents.md
Supports: Host loading and effective permission boundaries