| ★ |  Real-time Speech-to-Text APIs for Voice Agents: Beyond WER to Real-World Performance | | — | Estados Unidos | |
| 5 |  AssemblyAI's New Feature: Automatic Speaker Identification for Production Apps | | — | Estados Unidos | 88 |
| 7 |  Building AI Voice Agents with Vapi & AssemblyAI | | — | Estados Unidos | 88 |
| 9 |  Build an AI agent with LiveKit for real-time Speech-to-Text 🤖 | Full Python tutorial | | — | Estados Unidos | 88 |
| 10 |  Introducing new products and model updates for Voice AI applications | | — | Estados Unidos | 88 |
| 12 |  Build a Voice-Enabled AI Agent in Minutes | Microsoft Reactor @microsoftreactor | — | — | 87 |
| 14 |  Build a Voice-Enabled AI Agent in Minutes | Microsoft Reactor @microsoftreactor | — | — | 87 |
| 17 |  How to Evaluate APIs for Speaker Diarization | | — | Estados Unidos | 87 |
| 20 |  From Chat to Action: Understanding the OpenClaw System Architecture | Analytics Vidhya @analyticsvidhya | — | India | 87 |
| 6 |  How to Create a 24/7 AI Voice Agent for Your Business (Step-by-Step) | | 21.6K | Estados Unidos | 88 |
| 13 |  ElevenAgents: Configure, Deploy, and Improve AI agents at scale | | 5.6K | — | 87 |
| 19 |  From Idea to Live Voice Agent in Minutes (Claude Code) | | 2.7K | Estados Unidos | 87 |
| 18 |  ControlUp Field CTO Reveals How AI Is Resolving 61% of Endpoint Issues Automatically | | 1.7K | Estados Unidos | 87 |
| 15 |  OpenAI’s New Voice Secret | Ronald van Loon @ronald_vanloon | 847 | Países Bajos | 87 |
| 3 |  Real-Time vs Post-Call: Behind EdgeTier's Architecture 💡 | | 778 | Estados Unidos | 89 |
| 2 |  Your Ground Truth Is Wrong: Evaluating STT with truth files & semantic WER | AssemblyAI Workshop | | 404 | Estados Unidos | 89 |
| 16 |  How to Build a Real Time Agent Assist Voice Agent for Call Centers | | 388 | Estados Unidos | 87 |
| 1 |  Best Practices for Building High-Performance Voice Agents with AssemblyAI | | 194 | Estados Unidos | 92 |
| 11 |  What is Conversation Intelligence? AI Speech Analysis for Sales, Support & Product Teams | | 188 | Estados Unidos | 87 |
| 8 |  Step-Aware Voice Assistant on a Smartwatch Enabled by Multimodal Procedure Tracking and LLMs | | 68 | Estados Unidos | 88 |
| 4 |  Natural Language Processing in Conversational AI ( 10 Minutes) | Technology Whisper @technologywhisper | 3 | Singapur | 88 |