What is a Voice Step?
A Voice Step represents a conversational turn:- Assistant speaks — The configured script is spoken via text-to-speech
- User responds — The system listens and transcribes the response
- AI evaluates — The LLM analyzes the response against defined conditions
- Navigation — The conversation moves to the appropriate next step
Voice Step Structure
Writing Scripts
The script defines what your assistant communicates. Scripts can be written in two styles:Verbatim Scripts
Use the word “Say” when you want the assistant to speak exact wording:Instructional Scripts
Use describing words like “consider”, “ask about”, or “explain” for flexible delivery:Tips for Scripts
- Keep sentences short and clear
- Ask one question at a time
- Include natural transitions
Conditions
Conditions determine where the conversation goes based on the user’s response:How Conditions Are Evaluated
The AI doesn’t do simple keyword matching. Instead, it:- Understands context — Considers the full conversation history
- Interprets intent — Determines what the user actually means
- Matches conditions — Selects the most appropriate condition
- Generates response — Creates a natural response incorporating the next script
Special Conditions
Otherwise
The “otherwise” condition is a fallback when no specific condition matches:- Always include an “otherwise” condition
- Use it to handle unexpected responses gracefully
- Often loops back to clarify or rephrase
Ending the call from a condition
As well as a next step, a condition can end the flow or end the call. End Call lets the assistant finish speaking and still leaves the caller a short window to keep the call going; End Call (Strict) finishes the sentence and hangs up. See Where a condition can send the call.Question Answering
If the user asks a question that can be answered from the Knowledge Base or context, the assistant can respond without leaving the current step. This is handled automatically — the assistant answers the question and then continues with the current step’s flow.Interrupts
Voice steps are interruptible — users can speak over the assistant, causing it to stop and process the interruption. When an interrupt occurs, if the assistant believes it hasn’t fully conveyed its message for the step, it will attempt to repeat the key information before continuing. This ensures important details aren’t lost due to interruptions. The assistant can detect when its message has been cut off, but it doesn’t inherently “know” it has been interrupted in the conversational sense. See Assistant Behaviour for details on interrupt handling limitations.Best Practices
- One question per step — Don’t overload the user
- Anticipate responses — Think about all ways users might reply
- Include fallbacks — Use “Otherwise” to loop back to the current step
- Keep transitions natural — Next steps should flow from the response
- Test with real language — Users don’t speak in keywords
Next Steps
- Steps Overview — Learn about all step types
- Conversation Dynamics — Fine-tune timing and response behavior
- Variables — Use data in your scripts