Identify Speaker (1:N)
voice_id_identify1:N identification — rank everyone enrolled in the group against this clip.
Returns: dict with keys: candidates (list of {speaker_id, similarity}, best first).
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": {
"audio": "<audio>",
"group_id": "<group_id>"
},
"name": "voice_id_identify"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| audio | Yes | Base64-encoded WAV of the clip to identify | |
| top_k | No | How many candidate speakers to return | |
| group_id | Yes | The group/namespace to search within |