What is streaming (in voice AI)?
Processing audio and text in small pieces as they arrive, instead of waiting for the whole utterance.
Streaming (in voice AI), explained
Streaming speech-to-text produces words while the caller is still talking, and streaming text-to-speech starts speaking the first words of a reply while the rest is generated.
Streaming is the main technique that makes AI phone conversations feel real-time.
Streaming also enables barge-in: because the agent is listening continuously, it can notice the caller speaking and stop its own audio immediately.
See how these ideas come together in Chitti, Manolle's AI voice agent.
Related terms
- Latency (voice response time)The delay between the caller finishing speaking and hearing the agent's reply.
- Speech-to-text (STT)Technology that converts spoken audio into written text, also called automatic speech recognition (ASR).
- Text-to-speech (TTS)Technology that turns written text into spoken audio.
See an AI voice agent at work on your calls.
See the complete system live: marketing, lead capture, AI voice calling, sales conversion, and analytics.