Skip to content

Data requirements

Audio formats supported

All IDVoice SDK components can work with two types of audio input: raw audio samples (either PCM16 or PCM-Float) and audio files. WAV and Opus (*.opus or *.ogg) audio files are supported.

Supported types of WAV files are:

  • Unsigned 8-bit PCM
  • Signed 12-bit PCM
  • Signed 16-bit PCM
  • Signed 24-bit PCM
  • Signed 32-bit PCM
  • IEEE 32-bit floating point
  • IEEE 64-bit floating point
  • A-law and μ-law
  • Microsoft ADPCM
  • IMA ADPCM (DVI, format code 0x11)

Warning

Since Opus codec is lossy, a slight accuracy degradation is expected. However, the more codec compression is, the more accuracy degradation is expected. IDVoice can operate with almost no accuracy degradation with audio encoded using the following Opus code parameters: frame size >=20 ms bitrate, >=18 kbit/sec, encoding complexity >=5.

Sampling rates supported

IDVoice for microphone channel supports all sampling rates >=16 kHz.