Skill UI

Guides building async worker pipelines for real-time conversational voice agents with streaming transcription, LLM reasoning, and interrupt-aware TTS across providers.

OpenAI’s Whisper provides robust multilingual speech-to-text transcriptions, translations to English, and language detection across 99 languages, suitable for podcasts, meetings, and noisy audio workflows with CPU/GPU acceleration and batch or streaming modes.

This comprehensive skill provides an end-to-end solution for video and audio content creation. Users can upload videos from various sources (YouTube, local files) and perform advanced operations such as real-time streaming, semantic search, and complex editing (trimming, overlays). Key features include AI-powered transcription, subtitle generation, and the ability to generate diverse media assets like images, music, sound effects, and voiceovers, making it ideal for content creators and media professionals.

Enables an OpenClaw agent to place managed outbound phone calls for alerts, briefings, reminders, and urgent notifications without Twilio, combining REST-triggered dialing with transcription and TTS so conversations feel like chat.

This workflow provides comprehensive audio processing capabilities, covering both real-time streaming transcription (for live captions and voice agents) and advanced post-processing using LeMUR. Use it for summarizing long meetings, answering questions based on transcripts, extracting action items, and running custom LLM analyses on recorded audio.

Implement robust handling for AssemblyAI's asynchronous transcription completion events via webhooks. This guides users on how to set up secure endpoints that receive POST requests upon job completion or failure. It covers submitting transcripts with webhook URLs, verifying authentication headers, and processing the final transcript data, including running subsequent analyses like summarization.

This workflow implements Abridge's end-to-end clinical documentation pipeline. It captures ambient audio from patient encounters, performs real-time transcription, utilizes generative AI to structure the medical notes (e.g., SOAP, H&P), generates required medical codes (ICD-10, CPT), and finally inserts the structured data directly into the EHR system. Designed for primary clinical encounters, minimizing manual charting time.

A comprehensive guide to using AssemblyAI for rich audio processing. This guide covers basic speech-to-text transcription from URLs or local files, along with advanced AI features. Capabilities include speaker diarization, sentiment analysis, key phrase extraction, entity detection, and powerful LLM-powered analysis (LeMUR) for summarization and Q&A. Ideal for integrating deep, multi-faceted audio insights into applications.

This guide provides advanced techniques to optimize AssemblyAI's transcription performance for large-scale applications. Learn how to maximize throughput and minimize latency by implementing caching strategies (Redis/LRU), utilizing webhooks instead of polling, selecting the optimal speech model based on needs, and parallelizing batch processing workloads.

A comprehensive workflow suite for professional audio manipulation using ElevenLabs API. This module supports multiple advanced AI features, including Speech-to-Speech voice cloning, generating realistic sound effects from text prompts, isolating and removing background noise, and accurate Speech-to-Text transcription with diarization. Ideal for content creators, podcast producers, and audio engineers.

This guide provides a robust implementation for handling asynchronous webhooks from ElevenLabs. It covers the critical steps of receiving POST notifications (such as transcription completion, post-call audio, and failure events), performing secure HMAC-SHA256 signature verification, and routing the event data to specific processing handlers. Ideal for integrating ElevenLabs into conversational AI pipelines, ensuring data integrity and reliable background processing.