assemblyai-streaming

This skill should be used when working with AssemblyAI’s Speech-to-Text and LLM Gateway APIs, especially for streaming/live transcription, meeting notetakers, and voice agents that need low-latency transcripts and audio analysis.

Jump to install

Repository: ratacat/claude-skills
Last source activity: December 19, 2025 at 04:11
Detected SKILL.md language: English
Stars: 49
Forks: 9

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

A direct command skips the review prompt. Inspect the source before running it.

npx skills add https://github.com/ratacat/claude-skills --skill assemblyai-streaming

The command stays on one line. Scroll horizontally to inspect it before copying.

Prefer a local copy? Download the files currently available to SkillsMP.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

SKILL.md

Source instructions · Read-only preview

Back to search Back to installation

agent-native-audit

Run comprehensive agent-native architecture review with scored principles

2026-02-11

agent-native-reviewer

Use this agent when reviewing code to ensure features are agent-native - that any action a user can take, an agent can also take, and anything a user can see, an agent can see. This enforces the principle that agents should have parity with users in capability and context. <example>Context: The user added a new feature to their application.\nuser: "I just implemented a new email filtering feature"\nassistant: "I'll use the agent-native-reviewer to verify this feature is accessible to agents"\n<commentary>New features need agent-native review to ensure agents can also filter emails, not just humans through UI.</commentary></example><example>Context: The user created a new UI workflow.\nuser: "I added a multi-step wizard for creating reports"\nassistant: "Let me check if this workflow is agent-native using the agent-native-reviewer"\n<commentary>UI workflows often miss agent accessibility - the reviewer checks for API/tool equivalents.</commentary></example>

2026-02-11

ankane-readme-writer

Use this agent when you need to create or update README files following the Ankane-style template for Ruby gems. This includes writing concise documentation with imperative voice, keeping sentences under 15 words, organizing sections in the standard order (Installation, Quick Start, Usage, etc.), and ensuring proper formatting with single-purpose code fences and minimal prose. Examples: <example>Context: User is creating documentation for a new Ruby gem. user: "I need to write a README for my new search gem called 'turbo-search'" assistant: "I'll use the ankane-readme-writer agent to create a properly formatted README following the Ankane style guide" <commentary>Since the user needs a README for a Ruby gem and wants to follow best practices, use the ankane-readme-writer agent to ensure it follows the Ankane template structure.</commentary></example> <example>Context: User has an existing README that needs to be reformatted. user: "Can you update my gem's README to follow the Ankane style?" assistant: "Let...

2026-02-11

View all from this repository

name	assemblyai-streaming
description	This skill should be used when working with AssemblyAI’s Speech-to-Text and LLM Gateway APIs, especially for streaming/live transcription, meeting notetakers, and voice agents that need low-latency transcripts and audio analysis.
license	MIT
allowed-tools	["Read","Write","Edit","Grep","Glob","Bash","Python"]
metadata	{"skill-version":"1.0.0","upstream-docs":"https://www.assemblyai.com/docs","focus":"streaming-stt, meeting-notetaker, voice-agent, llm-gateway"}

AssemblyAI Streaming & Live Transcription Skill

Overview

Use this skill to build and maintain code that talks to AssemblyAI’s:

Streaming Speech-to-Text (STT) via WebSockets (wss://streaming.assemblyai.com/v3/ws)
Async / pre-recorded STT via REST (https://api.assemblyai.com/v2/transcript)
LLM Gateway for applying Claude/GPT/Gemini-style models to transcripts (https://llm-gateway.assemblyai.com)

The emphasis is on streaming/live transcription, meeting notetakers, and voice agents, while still covering async workflows and post-processing.

import assemblyai as aai from assemblyai.streaming import v3 as aai_stream import pyaudio API_KEY = "<YOUR_API_KEY>" aai.settings.api_key = API_KEY SAMPLE_RATE = 16000 CHUNK_MS = 50 FRAMES_PER_BUFFER = int(SAMPLE_RATE * (CHUNK_MS / 1000.0)) def main(): client = aai_stream.StreamingClient( aai_stream.StreamingClientOptions( api_key=API_KEY, api_host="streaming.assemblyai.com", # or "streaming.eu.assemblyai.com" ) ) def on_begin(_client, event: aai_stream.BeginEvent): print(f"Session started: {event.id}, expires at {event.expires_at}") def on_turn(_client, event: aai_stream.TurnEvent): # Use immutable transcript text text = (event.transcript or "").strip() if not text: return # Use formatted finals only for display; keep unformatted for LLMs if event.turn_is_formatted: print(f"[FINAL] {text}") else: print(f"[PARTIAL] {text}", end="\r") def on_terminated(_client, event: aai_stream.TerminationEvent): print(f"\nTerminated. Audio duration={event.audio_duration_seconds}s") def on_error(_client, error: aai_stream.StreamingError): print(f"\nStreaming error: {error}") client.on(aai_stream.StreamingEvents.Begin, on_begin) client.on(aai_stream.StreamingEvents.Turn, on_turn) client.on(aai_stream.StreamingEvents.Termination, on_terminated) client.on(aai_stream.StreamingEvents.Error, on_error) client.connect( aai_stream.StreamingParameters( sample_rate=SAMPLE_RATE, format_turns=False, # better latency for voice agents ) ) pa = pyaudio.PyAudio() stream = pa.open( format=pyaudio.paInt16, channels=1, rate=SAMPLE_RATE, input=True, frames_per_buffer=FRAMES_PER_BUFFER, ) try: print("Speak into your microphone (Ctrl+C to stop)...") def audio_gen(): while True: yield stream.read(FRAMES_PER_BUFFER, exception_on_overflow=False) client.stream(audio_gen()) except KeyboardInterrupt: pass finally: client.disconnect(terminate=True) stream.stop_stream() stream.close() pa.terminate() if __name__ == "__main__": main()

assemblyai-streaming

Install options

Review the source files

AssemblyAI Streaming & Live Transcription Skill

Overview

AssemblyAI Streaming & Live Transcription Skill

Overview

When to Use

AssemblyAI Mental Model

1. Products to care about

2. Key model knobs (Async)

3. Key model knobs (Streaming)

4. Regions and data residency

Security & API Keys

High-Level Workflow Patterns

Decision tree

How Claude Should Work with This Skill

General principles

Recipe 1 – Minimal Streaming from Microphone (Python SDK)

assemblyai-streaming

Source facts

Install options

Review the source files

More from this repository

More from this repository

AssemblyAI Streaming & Live Transcription Skill

Overview

AssemblyAI Streaming & Live Transcription Skill

Overview

When to Use

AssemblyAI Mental Model

1. Products to care about

2. Key model knobs (Async)

3. Key model knobs (Streaming)

4. Regions and data residency

Security & API Keys

High-Level Workflow Patterns

Decision tree

How Claude Should Work with This Skill

General principles

Recipe 1 – Minimal Streaming from Microphone (Python SDK)