**Realtime Speech-to-Text API** enables fast, accurate voice transcription using AssemblyAI’s WebSocket-based API. With sub-second latency and multilingual support, it provides the speech recognition layer while allowing you to use your own LLM, TTS, and orchestration for a fully customizable voice agent.
.png&w=256&q=75)
.png&w=256&q=75)
.png&w=256&q=75)
.png&w=256&q=75)