Skip to content

Added transcript voicemailDetectionType to call forwarding docs #565

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jul 9, 2025
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 13 additions & 1 deletion fern/call-forwarding.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -386,14 +386,18 @@ In this mode, Vapi dials the destination number and places the caller on hold (w
- Provide a `message` to be spoken to the operator when they answer.
- Optionally define a `summaryPlan` that will take precedence over the message if enabled.
- Configure a `fallbackPlan` with a message and whether to end the call if transfer fails.
- When voicemail detection is enabled in the assistant configuration (with either Google or OpenAI provider), it will use that configuration to detect if a human answered the call. Note that only Google or OpenAI providers are supported for voicemail detection with transfer plans, even if the assistant configuration supports other providers like Twilio or Vapi.
- Configure `voicemailDetectionType` to customize how human voice detection is performed (only applies when the provider is Google or OpenAI):
- `"audio"` (default): Supports a wide range of machine detection including beep detection and other audio cues
- `"transcript"`: Uses transcript-based detection with the lowest latency and faster transfer processing times
- Note that only Google or OpenAI providers are supported for voicemail detection with transfer plans, even if the assistant configuration supports other providers like Twilio or Vapi.

- **Example:**

```json
"transferPlan": {
"mode": "warm-transfer-experimental",
"message": "Transferring a customer to you.",
"voicemailDetectionType": "transcript",
"fallbackPlan": {
"message": "Could not transfer your call, goodbye.",
"endCallEnabled": true
Expand All @@ -414,6 +418,8 @@ In this mode, Vapi dials the destination number and places the caller on hold (w
}
```

<Note>This example uses `"transcript"` for the fastest transfer processing. For wider machine detection capabilities, use `"audio"` instead.</Note>

Here is a full example of a `transferCall` payload using the experimental warm transfer mode:

```json
Expand All @@ -430,6 +436,7 @@ Here is a full example of a `transferCall` payload using the experimental warm t
"transferPlan": {
"mode": "warm-transfer-experimental",
"message": "Transferring a customer to you.",
"voicemailDetectionType": "audio",
"fallbackPlan": {
"message": "Could not transfer your call, goodbye.",
"endCallEnabled": true
Expand All @@ -453,7 +460,12 @@ Here is a full example of a `transferCall` payload using the experimental warm t
}
```

<Note>This example uses `"audio"` for comprehensive machine detection including beep detection. This is the default option if not specified.</Note>

**Notes:**

- In all warm transfer modes, the `{{transcript}}` variable contains the full transcript of the call and can be used within the `summaryPlan`.
- The `voicemailDetectionType` parameter allows you to optimize the detection method based on your needs:
- Use `"transcript"` for the fastest transfer processing with lowest latency
- Use `"audio"` (default) for comprehensive machine detection including beep detection and other audio cues
- For more details about transfer plans and configuration options, please refer to the [transferCall API documentation](/api-reference/tools/create#request.body.transferCall.destinations.number.transferPlan)
Loading