Audio requirements for imported files
Audio you import into the system must meet certain requirements. Incorrectly formatted audio is not incorporated into the voiceprint model.
Audio property |
Requirement |
---|---|
File format |
WAV
|
Audio format |
16-bit Linear PCM or G.711 is strongly recommended.
NOTE: Audio in any audio format that was not created by a suite Recorder is unlikely to result in an audio segment that can be used for voiceprint model training due to implementation differences between the audio source and the suite Recorder. Export audio from an external system as a PCM or G.711 WAV file to guarantee compatibility. |
Sample rate |
8 kHz |
Channels |
The voice of one person in the channel used for enrollment. For a mono recording with multiple people speaking, use a third-party editing tool to derive an audio file containing only the voice of a single person. Imported audio is not diarized for enrollment purposes. |