Supported audio formats

SpeechKit recognizes and synthesizes audio in the following formats:

• LPCM
• OggOpus
• MP3

LPCMLPCM

Linear pulse-code modulation without a WAV header.

This audio format specifications include:

• Sampling rate:

  API version	Valid values
  Speech synthesis API v1	8, 16, or 48 kHz
  Speech synthesis API v3	Any value from 8 to 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: 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 any audio file quality and header restrictions.

MP3MP3

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

SpeechKit recognizes MP3 without any audio file quality and header restrictions.