get_recent_voice
Retrieve the most recent voice transcription segments with timestamps, transcript text, confidence scores, and duration to recall just-dictated content.
Instructions
Return the most recent N voice transcription segments captured by ContextPulse.
Returns segments with timestamp, transcript text, confidence score, and duration.
USE WHEN: the user references something they just dictated ("what did I just say", "use my last voice note"). NOT FOR: text search over older voice — use search_voice. ALTERNATIVES: search_voice (text query), find_related_context (cross-source).
BEHAVIOR: pure read from the voice transcript log. No side effects.
PARAMETERS: n: how many segments to return. Range 1-100. Default 10.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "get_recent_voice"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| n | No |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |