Sahil
03/25/2025, 5:53 AM157e3f15-5a58-4db7-95c2-2ce92cf8b768
a0471f25-c35b-4f20-8e6b-6c5cbf1dcaa7
Being honest, from a user's perspective this kind of issues makes us loose our interest to work with vapi.
Please look into this on priority and help me with some solution.Vapi Support Bot
03/25/2025, 5:55 AMvoice.chunkPlan.formatPlan
config to match your requirements.
2. **Speaking Plan Settings**: The startSpeakingPlan
configuration might need adjustment. Setting Deepgram's endpointing value to 300 has helped resolve similar issues for other users.
3. **Transcriber Issues**: You might want to try using modelOutputInMessages
instead of transcribed output in messages. This can be enabled by making an UPDATE request to your assistant.
## Known Bugs
There are some known bugs that could cause this behavior:
1. **Values Not Being Read**: There's a known issue where "the voice agent fails to read out loud the values retrieved from a search," resulting in silence or placeholders not being replaced with retrieved values.
2. **Tool Call Interpretation**: The model may interpret a tool call as spoken output instead of executing the command, which can affect how input parameters are spoken.
## Possible Solutions
Here are some steps you can take:
1. **Update Assistant Configuration**: Make an UPDATE assistant request using the API client or Postman to adjust the speaking plan and transcriber settings.
2. **Check SSML Settings**: Enabling SSML can give you more control over speech synthesis, including pauses and pronunciation.Vapi Support Bot
03/25/2025, 5:55 AMSahil
03/25/2025, 5:58 AMSahil
03/25/2025, 5:58 AMKings Big
03/26/2025, 1:36 PMKings Big
03/26/2025, 1:38 PMSahil
03/26/2025, 5:56 PMShubham Bajaj
03/30/2025, 11:37 AMenableSsmlParsing
is false, the system removes angle bracket content from the text via the removeAngleBracketContent
function. This could be stripping out parameter names if they're enclosed in formatting tags.
2. **Adjust Format Plan**: The assistant's voice format plan needs to be configured to preserve parameter names:
json
{
"voice": {
"enableSsmlParsing": true,
"chunkPlan": {
"enabled": true,
"formatPlan": {
"enabled": true,
"replacements": []
}
}
}
}
3. **Add Custom Replacements**: If needed, you can add custom replacements to ensure parameter names are spoken correctly:
json
"replacements": [
{
"type": "exact",
"key": "short description",
"value": "short description"
},
{
"type": "exact",
"key": "urgency",
"value": "urgency"
},
{
"type": "exact",
"key": "priority",
"value": "priority"
}
]
4. **Implement Tool Response Guidelines**: Based on the prompting guide found, include specific instructions in your system prompt to ensure proper parameter handling:
[Warning]
Do not modify or attempt to correct user input parameters or user input, Pass them directly into the function or tool as given.
[Response Guidelines]
When asking for input parameters, always state the complete parameter name before requesting its value.
For example, say "Please provide the short description of the issue" rather than just "of the issue."
5. **Update Assistant Configuration**: Make an API call to update your assistant with these changes:
javascript
// Example API call to update assistant configuration
const updateAssistant = {
voice: {
enableSsmlParsing: true,
chunkPlan: {
enabled: true,
formatPlan: {
enabled: true
}
}
},
model: {
systemPrompt: "... [include tool parameter handling instructions from above] ..."
}
};
// PUT request to /assistant/{assistantId}