Skip to content

LLM Streaming

Contact Center supervisors can enable real-time streaming of LLM responses, reducing latency and enhancing the user experience, particularly for voice interactions.

Steps to enable LLM Streaming:

  1. Go to Contact Center AI > CONFIGURATIONS > Advanced Settings > LLM Streaming.
    LLM Streaming

  2. Turn on the toggle to enable LLM streaming.

    Note

    LLM Streaming is disabled by default.

    Enable LLM Streaming

Benefits of LLM Streaming

  • Reduced Latency: Real-time streaming of rephrased responses significantly decreases the time taken for the user to receive the modified content.
  • Improved User Experience: Faster delivery of rephrased content creates a more natural and interactive conversation flow.
  • Simplified Process: Streamlining the rephrasing process reduces complexity and potential points of failure.

LLM Streaming for Text-to-Speech (TTS) Providers

LLM streaming is enabled for the following TTS providers:

  1. PlayHT
  2. ElevenLabs
  3. Deepgram

Note

If a GenAI node's response contains special characters, such as punctuation marks, symbols, or brackets, the system might fail to play the prompt during a call, resulting in silence for the caller.