---
title: "Identify Single Speaker Profile"
method: POST
path: "/text-independent/profiles/identifySingleSpeaker"
tags: ["text-independent"]
---

# Identify Single Speaker Profile

`POST /text-independent/profiles/identifySingleSpeaker`

Identifies who is speaking in input audio among a list of candidate profiles.

Limitations:
* Minimum audio input length is **1 second**
* Maximum audio input length is **120 seconds**
* Minimum candidate speakers count is **1**
* Maximum candidate speakers count is **50**
* Minimum effective speech length (excluding silence and other non-speech frames) is **4 seconds**
  This limitation can be disabled by setting "ignoreMinLength" to **true**.

* Minimum audio Signal-to-noise ratio (SNR) is **0dB**

## Query parameters

- `profileIds` string, required
- `ignoreMinLength` boolean

## Response `200`

OK

- IdentifiedSingleSpeakerInfo
  - `identifiedProfile` IdentifyInfo — Identified speaker info
    - `profileId` string, uuid — ID of identified of profile. If no candidate is identified as the right speaker, the value is set to empty GUID.
    - `score` number — A float number indicating the similarity between input audio and targeted voice print. This number must be between 0 and 1. A higher number means higher similarity.
  - `profilesRanking` IdentifyInfo[] — Object containing data of the top 5 profiles (including identified profile) sorted in descending order by score.
    - `profileId` string, uuid — ID of identified of profile. If no candidate is identified as the right speaker, the value is set to empty GUID.
    - `score` number — A float number indicating the similarity between input audio and targeted voice print. This number must be between 0 and 1. A higher number means higher similarity.

## Other responses

- `400` — Bad Request * InvalidRequest - Invalid audio length. Maximum allowed length per recognition request is 120 seconds. * InvalidRequest - Invalid audio length. Minimum allowed length per recognition request is 1 second. * InvalidRequest - Invalid audio format. Supported format is 16Khz 16bit Mono PCM. * InvalidArgument - Invalid ignoreMinLength parameter value. Valid values are "true" and "false". * InvalidArgument - Invalid profileIds parameter value. It should be comma-delimited list of IDs containing at least one ID. * InvalidRequest - profileIds parameter is missing. It should be comma-delimited list of IDs containing at least one ID. * InvalidRequest - Invalid group of profiles. Profiles must have the same locale. * InvalidRequest - Maximum number of profiles allowed per request is 50. * InvalidRequest - Minimum audio Signal-to-noise ratio (SNR) is 0dB * InvalidRequest - Profile is not enrolled.
- `401` — Request is not authorized. Make sure subscription key is included and valid.
- `415` — UnsupportedMediaType - Unsupported media type. Only "audio/wav; codecs=audio/pcm" is accepted.
- `429` — Rate limit is exceeded.
- `500` — Internal Server Error.

---

[API](https://skmtc.net/azure/apis/cognitiveservices-speakerrecognition-identification.md) · [All operations](https://skmtc.net/azure/apis/cognitiveservices-speakerrecognition-identification/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/azure/cognitiveservices-speakerrecognition-identification/revisions/a4878fa7e973/schema)