assemblyai

Transcribes audio files to text with word timings via the Pixazo API gateway.

Updated May 2, 2026
One-click install
npx skills add https://github.com/Pixazo-AI/skills --skill assemblyai-pixazo-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: assemblyai
Source: https://github.com/Pixazo-AI/skills/tree/main/skills/assemblyai
Command: npx skills add https://github.com/Pixazo-AI/skills --skill assemblyai-pixazo-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Converting audio recordings into accurate, timestamped text transcripts requires a speech recognition service, and this Skill lets an AI agent call AssemblyAI's Universal 3 Pro speech-to-text model through the Pixazo API without manual integration work. ## Core Features & Use Cases - Speech-to-Text Transcription: Submits an audio URL to the AssemblyAI Universal 3 Pro endpoint and returns a full transcript. - Word-Level Timings & Segmentation: Returns per-word timings, per-utterance segmentation, confidence scores, and detected language. - Managed API Key Flow: Guides the agent to acquire, store, and reuse a Pixazo API key from ~/.pixazo/api-key so the user only provides it once. - Use Case: A podcaster pastes a link to an episode recording and asks the agent to transcribe it; the agent calls the endpoint and returns the transcript with timestamps for show notes. ## Quick Start Ask the agent to transcribe the audio file at a given URL using AssemblyAI speech-to-text via Pixazo.

Frequently Asked Questions about assemblyai

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

FAQPage Schema
How do I transcribe an audio file with AssemblyAI through Pixazo?▼

Send a POST request to https://gateway.pixazo.ai/assemblyai-universal-3-pro/v1/speech-to-text with your Pixazo API key in the Ocp-Apim-Subscription-Key header and a JSON body containing the audio_url field pointing to your audio file.

What does the AssemblyAI speech-to-text API return?▼

The response contains the full transcript along with per-word timings, per-utterance segmentation, a confidence score, and the detected language. The call is synchronous, so no polling is required.

Where do I get a Pixazo API key for speech-to-text?▼

Sign in at https://api-console.pixazo.ai/api_keys, click Create new key, and copy it. The Skill saves it to ~/.pixazo/api-key so you only provide it once, or you can set the PIXAZO_API_KEY environment variable.

Why am I getting a 401 or 429 error from the Pixazo API?▼

A 401 means the API key is missing or invalid, so generate a fresh key at the Pixazo console. A 429 indicates rate limiting; wait about 5 seconds and retry the request once.

Can this Skill transcribe local audio files or only URLs?▼

The documented request accepts an audio_url field, so the audio must be accessible via a URL. Local files need to be uploaded to a reachable location first before being submitted for transcription.