Transcribe Audio to Markdown with Gemini 3.5 AI Skill

Transcribe Audio to Markdown with Gemini 3.5 AI Skill

This AI agent skill transcribes local audio files into Markdown format using the Gemini 3.5 Transcribe engine. It includes speaker labels and timestamps, making it suitable for various types of recordings such as interviews, meetings, lectures, podcasts, and voice notes.

What this skill does

• Normalizes audio files using a command-line interface (CLI).
• Uploads audio chunks to the Gemini 3.5 Transcribe service for processing.
• Generates a complete Markdown transcript with speaker diarization and word-level timestamps.
• Allows customization through optional input parameters such as language hints and vocabulary terms.
• Provides user feedback before uploading media, especially for long or potentially costly transcriptions.

Who it is for

• Developers and software teams using AI coding agents like Claude Code, Cursor, and Codex.
• Professionals involved in data analysis, transcription services, or content production.
• Teams looking to streamline transcription workflows, improve documentation consistency, and reduce repetitive manual tasks.

Use cases

• Transcribing interviews or meetings for more accessible documentation and review.
• Converting educational lectures into text for students and educators.
• Creating text versions of podcasts and voice content for accessibility purposes.
• Organizing and archiving voice notes into structured and searchable text files.

Technical details

• Utilizes the Gemini 3.5 Transcribe API for audio processing.
• Employs speaker diarization for identifying individual speakers in audio.
• Supports word-level timestamps to maintain context and accuracy.
• Configurable chunk duration for processing, with a default of 30 minutes.
• Relies on environment settings for API keys and supports the use of fallback keys such as GOOGLE_API_KEY.

Source & Licence

This package is built on open-source work published by iurysza (iurysza/agent-skills) and distributed under MIT. The original licence text and copyright notice are included in your download.

Personal and commercial use, modification and redistribution are permitted, provided the original copyright and licence notice are retained.

Your purchase covers curation, licence verification, packaging, documentation and instant delivery. It does not grant exclusive rights to the underlying open-source code, which remains available under its original licence.

Delivery & Support

• Delivery: instant — a secure download link is emailed to you as soon as payment is confirmed.
• Format: ZIP archive containing the skill files, documentation and the original licence.
• Support: support@mcpcart.com — we aim to reply within 2 business days.
• Updates: updates are included only where stated on this page.

Refunds

This is a digital product delivered immediately after purchase. By completing your order you request immediate delivery and acknowledge that, once the download has been accessed, the statutory right to cancel no longer applies to the extent permitted by law. Refund requests are handled in accordance with our published Refund Policy.

Claude, Codex, Gemini and Cursor are trademarks of their respective owners. MCP Cart is an independent marketplace and is not affiliated with, endorsed by, or sponsored by any of them. Compatibility references describe interoperability only.