skills.rest
calesthio
calesthioCOMMUNITY
Explore all skills by this author →
𝕏@calesthioailabsGitHub

assemblyai-transcription

Convert recorded or live speech into timecoded transcripts and captions via AssemblyAI.

123|21|Updated Jul 11, 2026
Search Tags:#captions#transcription#audio production#speech-to-text#assemblyai#speaker diarization#pii redaction
One-click install
npx skills add https://github.com/calesthio/generative-media-skills --skill assemblyai-transcription
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: assemblyai-transcription
Source: https://github.com/calesthio/generative-media-skills/tree/main/skills/providers/speech-to-text/assemblyai-transcription
Command: npx skills add https://github.com/calesthio/generative-media-skills --skill assemblyai-transcription

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps media teams turn recorded or live speech into accurate, reviewable transcripts and timecoded production assets without improvising provider configuration, lifecycle management, privacy controls, or quality assurance.

Core Features & Use Cases

  • Transcription Surface Selection: Choose pre-recorded, synchronous short-file, or real-time streaming transcription based on duration, latency, and production needs.
  • Production Transcript Workflows: Configure diarization, speaker identification, language detection, code-switching, keyterms, captions, subtitles, timestamps, summaries, chapters, entities, sentiment, translation, profanity filtering, and PII redaction.
  • Operational Guardrails: Plan webhooks, rate limits, retries, billing, retention, consent, API-key security, data controls, and human review for production delivery.
  • Use Case: Prepare a podcast package with a speaker-reviewed transcript, SRT and VTT caption drafts, chapter markers, pull-quote candidates, and privacy-aware derivative artifacts.

Quick Start

Use the AssemblyAI transcription skill to create a production plan for the attached interview, including the appropriate API surface, speaker strategy, caption outputs, privacy controls, webhook lifecycle, and final QA checks.

Frequently Asked Questions about assemblyai-transcription

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate SRT and VTT caption files from recorded speech?▼

Speaker diarization identifies and separates individual speakers within recorded audio, producing reviewable transcripts with labeled turns. It is essential for accurately attributing dialogue in podcasts, interviews, and multi-speaker webinars.

How does speaker diarization work for podcast transcription?▼

Speaker diarization identifies and separates individual speakers within recorded audio, producing reviewable transcripts with labeled turns. It is essential for accurately attributing dialogue in podcasts, interviews, and multi-speaker webinars.

Can I redact PII from audio transcripts automatically?▼

Real-time streaming transcription converts live speech into immediate text with low latency, using synchronous API surfaces and streaming tokens. It is necessary for live captions and voice-agent turns where immediate text output is required.

What is the best way to handle multilingual localization for audio transcripts?▼

The best approach for multilingual localization utilizes language detection, code-switching support, and translation features within the transcription workflow. This yields localized production transcripts and caption drafts for global audiences.

Do I need webhooks to manage pre-recorded transcription lifecycle?▼

Webhooks are required to handle asynchronous pre-recorded transcription lifecycle events, managing rate limits, retries, and billing. They provide operational guardrails for production delivery without polling the API surface.

What are the limitations of synchronous short-file transcription?▼

Synchronous short-file transcription is limited by duration constraints and rate limits compared to pre-recorded or real-time streaming surfaces. It is unsuitable for long-form podcasts or live captions requiring webhook lifecycle management.

Related Skills

Explore More Design & Creative Skills→
aztr0nutzsaztr0nutzs
1

Deepgram Speech-to-Text SDK

Transcribe live audio streams and pre-recorded files via Deepgram SDK.

Community
Intermediate
skills-ilskills-il
6

hebrew-podcast-postproduction

Generate a Hebrew podcast post-production bundle from a transcript or SRT file.

Official
Advanced
davidrrowleydavidrrowley

azure-ai-voicelive-dotnet

Enable bidirectional AI voice sessions in .NET using WebSockets and Azure authentication.

Community
Intermediate
imMamdouhaboammarimMamdouhaboammar

agency-voice-ai-integration-engineer

Design speech transcription pipelines with local Whisper and cloud ASR services.

Community
Advanced