[[WRITE: voice pipeline headline]]
[[WRITE: intro — generic real-time voice pipeline, anchored on RegalaUnaLlamada]]
Audio capture
[[WRITE: how audio is captured / streamed]]
Speech-to-text (STT)
[[WRITE: streaming STT approach, latency budget]]
LLM reasoning
[[WRITE: prompt/agent orchestration, tool use]]
Text-to-speech (TTS)
[[WRITE: streaming TTS, barge-in handling]]
Realtime transport
[[WRITE: transport, turn-taking, latency]]