process_voice_input
Processes voice session transcripts to identify learning intent, logs student interactions, updates mastery levels, and generates spoken responses.
Instructions
Processes spoken input from a voice session: detects intent from transcript keywords, logs the interaction with voice-specific fields, updates mastery if a learning-related intent is detected, and returns a structured spoken response.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"studentId": "<studentId>",
"sessionId": "<sessionId>",
"transcript": "<transcript>",
"audioDurationSeconds": "<audioDurationSeconds>"
},
"name": "process_voice_input"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| sessionId | Yes | The active voice session ID | |
| studentId | Yes | The student ID | |
| transcript | Yes | The speech-to-text transcript of the student's utterance | |
| audioDurationSeconds | Yes | Duration of the audio input in seconds |