Synchronous audio recognition
Synchronous audio recognition ensures fast response times and is suitable for pre-recorded small single-channel audio fragments.
If you want to recognize speech over the same connection, use streaming mode. In streaming mode, you can get intermediate recognition results.
Audio requirements
The audio you send must meet the following requirements:
- Maximum file size: 1 MB
- Maximum length: 30 seconds
- Maximum number of audio channels: 1
If your file is larger, longer, or has more audio channels, use asynchronous recognition.
SpeechKit allows you to recognize and synthesize the following audio formats:
- LPCM
- OggOpus
- MP3
For more information about each format's special features, see Supported audio formats.