PVQA: voice quality of a recording
pvqa_analyzeNon-intrusive voice quality analysis (Sevana PVQA) of an uploaded WAV file: predicted MOS (1-5) and the impairments found (low SNR, noise, dead air, clipping, clicks, echo, packet-loss artifacts, ...). No reference recording is needed. report_type "extended" adds the per-interval detector table.
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": {
"upload_id": "<upload_id>"
},
"name": "pvqa_analyze"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| channel | No | channel to analyze, from 0 (default 0); -1 mixes all channels | |
| upload_id | Yes | upload_id of a WAV file | |
| report_type | No | "basic" (default) or "extended" (adds the per-interval table) |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| mos | Yes | predicted MOS (1-5); null when the file has no speech to score | |
| channel | Yes | ||
| rfactor | No | share of good intervals (0-1) | |
| timeline | No | per-interval detector values (report_type=extended only) | |
| intervals | Yes | ||
| is_silent | Yes | true when the file contains no signal | |
| mos_model | No | name of the learned MOS model that produced the score | |
| upload_id | Yes | ||
| impairments | Yes | detectors that fired, with their interval counts |