Agent skill · software engineering · jeremylongshore
assemblyai-core-workflow-b
Analyze and operate an AssemblyAI Streaming v3 session with safe tokens, audio framing, turn handling, and explicit termination. Use when building live captions or voice agents. Trigger with "AssemblyAI streaming", "AssemblyAI v3 WebSocket", or "live transcript".
Why this skill is useful
Adds executable scripts for real-time streaming transcription and LLM integration that extend the AI's capabilities in audio processing.
What it needs
Requires assemblyai, sox installed locally. Requires assemblyai account access. About 2k tokens when loaded. Last updated 2026-08-07. 2,604 stars on the source repository.
What this skill does
AssemblyAI Streaming v3 Session Overview Operate live transcription around the current v3 message and billing lifecycle. Govern capture, credentials, finalized content, reconnects, and termination separately. Prerequisites The target repository or integration path and the requested operator outcome. The AssemblyAI project, environment, region, data classification, and accountable owner. Current first-party documentation plus credentials only for a narrowly approved live check. Current Contract Use wss://streaming.assemblyai.com/v3/ws or the approved residency host. Handle Begin, partial and finalized Turn messages, and Termination. Match encoding and sample rate, pace audio correctly, use backend-minted tokens in untrusted clients, and terminate explicitly so abandoned connections do not continue billing. Authentication For live work, inject ASSEMBLYAIAPIKEY from an approved secret manager and send the raw value only in the AssemblyAI Authorization header to the configured first-party host. Never print, commit, place in a URL, or expose it to an untrusted client. Callback secrets and temporary streaming tokens are separate credentials. Instructions 1. Confirm live-capture consent, region, model, encoding, and turn policy. 2. Mint a short-lived single-use token for untrusted clients. 3. Verify Begin before sending correctly paced audio frames. 4. Order turns and persist only approved finalized content. 5. Treat reconnect as a new governed session boundary. 6. Send termination, await confirmation, stop capture, and record duration. Tool Discipline Use Read, Glob, and Grep to inspect repository code, configuration, fixtures, and evidence. Use Write and Edit only for approved implementation or documentation changes. Do not call AssemblyAI, upload audio, open a streaming session, mint a token, replay a callback, deploy, rotate a key, or delete a transcript merely because this skill was invoked. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills jeremylongshore/assemblyai-core-workflow-b