Skip to content
POST/api/v1/eval/voice

Run voice-eval suite

Runs EvalGuard's 16 voice scorers over a supplied TRANSCRIPT (not audio): word-error-rate, transcription-accuracy, pronunciation-accuracy, signal-to-noise-ratio, audio-quality, speech-pace, silence-gap-detection, turn-taking-quality, voice-response-latency, abrupt-disconnection, ai-interrupting-user, user-interrupting-ai, user-interrupts, voice-sentiment, voice-user-satisfaction, vocal-affect. Body (strict): `transcript` (required, <= 1M chars), optional `reference` (ground truth for WER/CER), `input`, `projectId` (when set, org membership is verified), `scorers` (subset, <= 64 — an unknown name returns 400 UNKNOWN_SCORER; omit to run all), `metadata` (acoustic signals: snrDb, sampleRateHz, clippingRatio, naturalnessMOS, silenceRatio...) and per-scorer `options`. Returns { results[], summary{total,passed,failed,avg_score}, latency_ms }; a scorer that throws is reported as score 0 / passed false rather than failing the request. Audited as `eval_run` on resourceType `voice-eval`; 60 req/min.

Authentication

Send Authorization: Bearer YOUR_API_KEY on every request. Generate API keys at /dashboard/settings/api-keys.

Request body required

Example

{
  "transcript": "string",
  "reference": "string",
  "input": "string",
  "projectId": "00000000-0000-0000-0000-000000000000",
  "scorers": [
    "string"
  ],
  "metadata": {},
  "options": {}
}
Schema
{
  "application/json": {
    "schema": {
      "type": "object",
      "properties": {
        "transcript": {
          "type": "string",
          "minLength": 1,
          "maxLength": 1000000
        },
        "reference": {
          "type": "string",
          "maxLength": 1000000
        },
        "input": {
          "type": "string",
          "maxLength": 100000
        },
        "projectId": {
          "type": "string",
          "format": "uuid",
          "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
        },
        "scorers": {
          "maxItems": 64,
          "type": "array",
          "items": {
            "type": "string",
            "minLength": 1,
            "maxLength": 128
          }
        },
        "metadata": {
          "type": "object",
          "additionalProperties": {}
        },
        "options": {
          "type": "object",
          "additionalProperties": {
            "type": "object",
            "additionalProperties": {}
          }
        }
      },
      "required": [
        "transcript"
      ],
      "additionalProperties": false
    }
  }
}

Response

202 example

{
  "run_id": "00000000-0000-0000-0000-000000000000"
}

All status codes

200OK.
202Eval queued.
400(no description)
401(no description)
403Forbidden — the credential is valid but lacks the API-key scope, member role, or plan entitlement this operation requires.
429(no description)
500Internal Server Error — an unhandled error was converted to the standard error envelope (INTERNAL_ERROR).

Code samples

cURL

curl -X POST \
  https://evalguard.ai/api/v1/eval/voice \
  -H "Authorization: Bearer $EVALGUARD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "transcript": "string", "reference": "string", "input": "string", "projectId": "00000000-0000-0000-0000-000000000000", "scorers": [ "string" ], "metadata": {}, "options": {} }'

TypeScript

// The TypeScript SDK (@evalguard/sdk) exposes TYPED methods — runEval,
// getEval, runSecurityScan, checkFirewall, … — not a generic request().
// For an arbitrary endpoint, call it directly:

const res = await fetch("https://evalguard.ai/api/v1/eval/voice", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.EVALGUARD_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "transcript": "string",
    "reference": "string",
    "input": "string",
    "projectId": "00000000-0000-0000-0000-000000000000",
    "scorers": [
      "string"
    ],
    "metadata": {},
    "options": {}
  }),
});
console.log(res.status, await res.json());

Python

# The Python SDK (pip install evalguardai) exposes TYPED methods on
# EvalGuardClient — run_eval, get_eval, … — not a generic request().
# For an arbitrary endpoint, call it directly:

import os
import requests

headers = {"Authorization": f"Bearer {os.environ['EVALGUARD_API_KEY']}"}
headers["Content-Type"] = "application/json"

response = requests.request(
    "POST",
    "https://evalguard.ai/api/v1/eval/voice",
    headers=headers,
    json={
    "transcript": "string",
    "reference": "string",
    "input": "string",
    "projectId": "00000000-0000-0000-0000-000000000000",
    "scorers": [
        "string"
    ],
    "metadata": {},
    "options": {}
},
)
print(response.status_code, response.json())

Go

package main

import (
	"context"
	"fmt"
	"net/http"
	"os"
	"strings"
)

func main() {
	body := strings.NewReader(`{"transcript":"string","reference":"string","input":"string","projectId":"00000000-0000-0000-0000-000000000000","scorers":["string"],"metadata":{},"options":{}}`)
	req, _ := http.NewRequestWithContext(context.Background(), "POST", "https://evalguard.ai/api/v1/eval/voice", body)
	req.Header.Set("Authorization", "Bearer "+os.Getenv("EVALGUARD_API_KEY"))
	req.Header.Set("Content-Type", "application/json")
	resp, err := http.DefaultClient.Do(req)
	if err != nil { panic(err) }
	defer resp.Body.Close()
	fmt.Println(resp.Status)
}

Errors

400401403429500

Other Evals endpoints