AssemblyAI and Cartesia split voice agents by layer
AssemblyAI and Cartesia now compete across speech synthesis, transcription and orchestration, with different language coverage, pricing and benchmarks.
AssemblyAI guide details how text shapes TTS delivery
AssemblyAI says natural-sounding speech depends on wording, punctuation and disfluencies, with guidance on fillers, false starts and pacing.
AssemblyAI says Sync HTTP has a niche role beside streaming STT
AssemblyAI argues Universal-3.6 Pro Realtime should remain the default for voice agents, with Sync HTTP used for second passes and recovery.
AssemblyAI says coding agents beat visual builders for voice apps
AssemblyAI argues that spec-first coding agents can build and maintain voice agents more flexibly than point-and-click builders.
AssemblyAI details voice agent build with STT, LLM Gateway and TTS
AssemblyAI published a build guide showing how its streaming speech-to-text, LLM Gateway and text-to-speech services can power one voice agent loop.
AssemblyAI launches Universal-3 Pro promptable speech model
AssemblyAI launched Universal-3 Pro, a promptable speech model for transcription, speaker labeling, audio tagging and domain-specific accuracy gains.
AssemblyAI and LiveKit outline production voice agent stack
AssemblyAI describes a Python voice agent build that pairs LiveKit transport with its STT, LLM Gateway and TTS on one key.
AssemblyAI details a compliant AI cold-calling agent build
AssemblyAI outlined a structured outbound voice agent using Twilio, Universal-3.6 Pro Realtime, LLM Gateway and Text-to-Speech.
AssemblyAI details Python voice agent build with tool calling
AssemblyAI published a Python tutorial for a real-time voice agent that combines streaming speech recognition, LLM Gateway and text-to-speech.
AssemblyAI details raw WebSocket voice agent build with no SDK
AssemblyAI published a tutorial for building a voice agent directly on WebSockets with streaming STT, LLM Gateway and TTS.