Problem is the Voice input for things like prices gets formatted like this Voice input: The previous valuation for your property at 19 Inverness Terrace was £5 0 0 0 0 0. Which makes the model read out word by word rather than the amount. Any idea why this is happening? call id ca99b92e-76c0-4260-99eb-235f3789d594

Hi there! 👋 I see you're having an issue with voice input formatting prices incorrectly. I don't have specific information about the call ID you mentioned, but I can definitely help explain why your price is being read out digit by digit instead of as a complete amount! This issue is likely related to how the voice formatting system handles numbers. According to the [documentation](https://docs.vapi.ai/assistants/voice-formatting-plan), there are a few potential causes: 1. **Number-to-Digits Cutoff Setting**: The system has a setting called

numberToDigitsCutoff

that determines when numbers are read as digits instead of words. By default, this is set to the current year (2025), which means larger numbers might be read digit by digit. 2. **Voice Input Formatting Function**: The "Voice Input Formatted" function is enabled by default and tries to clean up text for better TTS output, but it might be misinterpreting your price format. The good news is this can be fixed! You can adjust the

formatPlan

in your assistant's voice configuration like this:

json
{
  voice: {
    chunkPlan: {
      formatPlan: {
        numberToDigitsCutoff: 1000000 // Set this higher than your largest expected number
      }
    }
  }
}

According to [troubleshooting information](https://discord.com/channels/1211482211119796234/1211483291191083018/threads/1342349738032500736), this should help the system interpret "£500000" as "five hundred thousand pounds" instead of reading each digit separately. Alternatively, you could try enabling

modelOutputInMessages

to use the model's output directly instead of the transcribed output, which might help with formatting issues as mentioned in [this discussion](https://discord.com/channels/1211482211119796234/1211483291191083018/threads/1334184334361628734). Is there anything else you'd like to know about fixing this voice formatting issue? Sources: - [Voice Formatting Plan](https://docs.vapi.ai/assistants/voice-formatting-plan)

checking if this is resolved/solved for you?