Supported audio formats

SpeechKit allows you to recognize and synthesize the following audio formats:

• LPCM
• OggOpus
• MP3

LPCMLPCM

Linear pulse-code modulation without a WAV header.

Audio features in this format:

• Sampling frequency:

  API version	Acceptable values
  Speech synthesis API v1	8, 16, or 48 kHz
  Speech synthesis API v3	Any value between 8 and 48 kHz
  Speech recognition API v2	8, 16, or 48 kHz
  Speech recognition API v3	8, 16, or 48 kHz

• Bit depth: 16 bit.

• Byte order: Reversed (little-endian).

• Audio data is stored as signed integers.

OggOpusOggOpus

For OggOpus, data is encoded using the OPUS audio codec and compressed using the OGG container format.

SpeechKit recognizes and synthesizes OggOpus without audio file quality and header restrictions.

MP3MP3

For MP3, data is encoded using the MPEG-1/2/2.5 Layer III audio codec and packaged in an MP3 container.

SpeechKit recognizes MP3 without audio file quality and header restrictions.