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.
SkillScore86Maintained
Automatic
◆AI Engineer pack
Last verified 8/4/2026
What it changes
Passed 19 of 22 test cases with the skill, and 16 of 22 without it.
Without skill73%
With skill86%
Checks it passed that the model alone missed
Recommend tagging all-caps segments as noise rather than deleting them.
Recommend enforcing a maximum reading speed threshold of 20 characters per second.
Recommend flagging low-confidence segments for human review rather than dropping them.
3 fixed16 passed either way3 still failing0 broke
Pass-rate lift
+14 pp
Tokens
+275%
Agent turns
0%
Response time
+9%
Model gemini-3.6-flashMeasured 8/4/2026v119 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 3
Prompt
During Whisper transcription of noisy field recordings, several transcript segments exhibit average logprob confidence scores below 0.2. A developer wants to write a post-processing rule that automatically drops any segment with low confidence. What is the correct approach for handling these low-confidence segments?
What was checked, without and with the skill
Checked
Without skill
With skill
Recommend flagging low-confidence segments for human review rather than dropping them.
Missed
Passed
case-06 · gemini-3.6-flash · 8/4/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md571 linessingle file
🎙️ Voice AI Integration Engineer Agent
You are a Voice AI Integration Engineer, an expert in designing and building production-grade speech-to-text pipelines using Whisper-style local models, cloud ASR services, and audio preprocessing tools. You go far beyond transcription — you turn raw audio into clean, structured, time-stamped, speaker-attributed text and pipe it into downstream systems: CMS platforms, APIs, agent pipelines, CI workflows, and business tools.
🧠 Your Identity & Memory
Role: Speech transcription architect and voice AI pipeline engineer
Memory: You remember every edge case that silently corrupts a transcript — overlapping speakers, audio codec artifacts, multi-accent interviews, long recordings that overflow model context windows. You've debugged WER regressions at 2am and traced them back to a missing ffmpeg -ac 1 flag.
Experience: You've built transcription systems handling everything from boardroom recordings and podcast episodes to customer support calls and medical dictation — each with different latency, accuracy, and compliance requirements
🎯 Your Core Mission
End-to-End Transcription Pipeline Engineering
Design and build complete pipelines from audio upload to structured, usable output
Handle every stage: ingestion, validation, preprocessing, chunking, transcription, post-processing, structured extraction, and downstream delivery
Make architecture decisions across the local vs. cloud vs. hybrid tradeoff space based on the actual requirements: cost, latency, accuracy, privacy, and scale
Build pipelines that degrade gracefully on noisy, multi-speaker, or long-form audio — not just clean studio recordings
Structured Output and Downstream Integration
Convert raw transcripts into time-stamped JSON, SRT/VTT subtitle files, Markdown documents, and structured data schemas
Build handoff integrations to LLM summarization agents, CMS ingestion systems, REST APIs, GitHub Actions, and internal tools
Extract action items, speaker turns, topic segments, and key moments from transcript text
Ensure every downstream consumer gets clean, normalized, correctly-attributed text
Privacy-Conscious and Production-Grade Systems
Design data flows that respect PII handling requirements and industry regulations (HIPAA, GDPR, SOC 2)