RecognizeAudio
Last updated: 2026-08-14 16:33:17Download PDF
1. API Description
Domain name for API request: mps.intl.tencentcloudapi.com.
This API is used to return the speech recognition results synchronously.
A maximum of 5 requests can be initiated per second for this API.
We recommend you to use API Explorer
Try it
API Explorer provides a range of capabilities, including online call, signature authentication, SDK code generation, and API quick search. It enables you to view the request, response, and auto-generated examples.
2. Input Parameters
The following request parameter list only provides API request parameters and some common parameters. For the complete common parameter list, see Common Request Parameters.
| Parameter Name | Required | Type | Description |
|---|---|---|---|
| Action | Yes | String | Common Params. The value used for this API: RecognizeAudio. |
| Version | Yes | String | Common Params. The value used for this API: 2019-06-12. |
| Region | No | String | Common Params. This parameter is not required for this API. |
| AudioData | Yes | String | Base64-encoded audio data. |
| Source | No | String | Identify the target language. If left empty, the default is auto for automatic language identification. Note: If the automatic language recognition performance is poor, you can specify the language to improve accuracy. Currently supported languages: auto-identification Simplified Chinese en: English Japanese ko: Korean vi: Vietnamese ms: Malay id: Indonesian fil: Filipino th: Thai pt: Portuguese tr: ar: Arabic es: Spanish hi: Hindi French de: German Italian Cantonese ru: Russian af: Afrikaans sq: Albanian am: Amharic hy: Armenian az: Azerbaijani eu: Basque bn: Bengali bs: Bosnian bg: Bulgarian my: Burmese ca: Catalan hr: Croatian cs: Czech da: Danish nl: Dutch et: Estonian fi: Finnish gl: Galician ka: Georgian el: Greek gu: Gujarati iw: Hebrew hu: Hungarian is: Icelandic jv: Javanese kn: Kannada kk: Kazakh km: Khmer RPC lo: Lao lv: Latvian lt: Lithuanian mk: Macedonian ml: Malayalam mr: Marathi mn: Mongolian ne: Nepali Norwegian Bokmål fa: Persian pl: Polish ro: Romanian sr: Serbian si: Sinhalese sk: Slovak sl: Slovenian Southern Sotho su: Sundanese sw: Swahili sv: Swedish ta: Tamil te: Telugu ts: Tsonga.uk: Ukrainian ur: Urdu uz: Uzbek ve: Venda xh: isiXhosa zu: Zulu |
| AudioFormat | No | String | Audio data format, default is pcm Supported formats: pcm (mono 16-bit sampling pcm data with a 16000 sampling rate) ogg-opus (mono Opus-encoded Ogg data with sample rates of 16000, 24000, or 48000). |
| SampleRate | No | Integer | Audio sampling rate Supported sampling rates: pcm 16000 ogg-opus 16000 / 24000 / 48000 |
| UserExtPara | No | String | Extended parameter. This is left empty by default. Use this parameter for special requirements. |
3. Output Parameters
| Parameter Name | Type | Description |
|---|---|---|
| Text | String | Recognition result of the entire audio. |
| AudioLength | Float | Audio duration, in seconds. |
| Sentence | Array of RecognizeAudioSentence | Recognition results of individual sentences. |
| RequestId | String | The unique request ID, generated by the server, will be returned for every request (if the request fails to reach the server for other reasons, the request will not obtain a RequestId). RequestId is required for locating a problem. |
4. Example
Example1 RecognizeAudio
Input Example
POST / HTTP/1.1
Host: mps.intl.tencentcloudapi.com
Content-Type: application/json
X-TC-Action: RecognizeAudio
<Common request parameters>
{
"Source": "zh",
"AudioFormat": "pcm",
"AudioData": "KwDn/zIA5v///wUA0v8D"
}Output Example
{
"RequestId": "f27f3866-3882-4c18-a4ac-3b3d83fd2f5a",
"Response": {
"AudioLength": 4.2,
"RequestId": "f27f3866-3882-4c18-a4ac-3b3d83fd2f5a",
"Sentence": [
{
"End": 3.59,
"Start": 0.03,
Hold the third and fourth meetings at the Great Hall of the People.
"WordsInfo": [
{
"End": 0.27,
"Start": 0.03,
"Word": "In"
},
{
"End": 0.43,
"Start": 0.27,
Person
},
{
"End": 0.51,
"Start": 0.43,
"Word": "People"
},
{
"End": 0.71,
"Start": 0.51,
Big
},
{
"End": 0.91,
"Start": 0.71,
Will
},
{
"End": 1.07,
"Start": 0.91,
Hall
},
{
"End": 1.55,
"Start": 1.39,
"Word": "Lift"
},
{
"End": 1.71,
"Start": 1.55,
Row
},
{
"End": 1.95,
"Start": 1.75,
Word
},
{
"End": 2.15,
"Start": 1.95,
Three
},
{
"End": 2.39,
"Start": 2.15,
Time
},
{
"End": 2.75,
"Start": 2.47,
"Word": "and"
},
{
"End": 2.91,
"Start": 2.75,
"Word": "The"
},
{
"End": 3.11,
"Start": 2.91,
Four
},
{
"End": 3.27,
"Start": 3.11,
Time
},
{
"End": 3.51,
"Start": 3.31,
Will
},
{
"End": 3.59,
"Start": 3.51,
"Word": "Discussion."
}
]
}
],
The third and fourth meetings were held at the Great Hall of the People.
}
}5. Developer Resources
SDK
TencentCloud API 3.0 integrates SDKs that support various programming languages to make it easier for you to call APIs.
- Tencent Cloud SDK 3.0 for Python
- Tencent Cloud SDK 3.0 for Java
- Tencent Cloud SDK 3.0 for PHP
- Tencent Cloud SDK 3.0 for Go
- Tencent Cloud SDK 3.0 for Node.js
- Tencent Cloud SDK 3.0 for .NET
- Tencent Cloud SDK 3.0 for C++
Command Line Interface
6. Error Code
The following only lists the error codes related to the API business logic. For other error codes, see Common Error Codes.
| Error Code | Description |
|---|---|
| InternalError.RecognitionError | Recognition error. |
| InvalidParameterValue.AudioData | Invalid audio data. |
| InvalidParameterValue.AudioDataTooLong | The audio data is too long. |
| InvalidParameterValue.AudioFormat | Unsupported audio data format. |
| InvalidParameterValue.SampleRate | Invalid audio sample rate. |
| InvalidParameterValue.SourceLanguage | A SourceLanguage parameter error occurs. |
| ResourceNotFound.UserUnregister | The user is not registered. |