Types

V‑Spark converts audio before passing it to the ASR engine for transcription, and so supports a wide variety of audio file formats. That said, audio attributes have a significant impact on the accuracy of ASR transcription, and conversion cannot account for voice data lost due to suboptimal recording and encoding. The level of accuracy for a given transcript affects analytics performance, making audio format and properties key considerations.

The best format for audio submitted for transcription and analysis is lossless G.711 WAV (PCM, uLaw, or aLaw).

Channels

Audio submitted for transcription and analysis must have one or two channels. The number of channels in source audio, along with how those channels are used, affects V‑Spark's ability to distinguish between speaker roles. In most cases, these roles are agent and client, and distinguishing between the two is critical for transcript analysis.

Transcription and analysis work best with two-channel (stereo) audio that has each speaker role on a separate channel. Audio with more than one speaker on the same channel may be diarized, a process that separates the audio into two channels and assigns each speaker to a different channel.

Evaluate

Use V‑Spark's built-in audio evaluation tool to verify audio properties, and to configure folder settings to match those properties.

The audio evaluator shows audio properties for the uploaded file, including the number of channels, and whether the audio is supported by V‑Spark. Files submitted for evaluation are not saved.

To use the audio evaluator:

1. Click Will my audio work? on the V‑Spark homepage or in the General section of the Help page.
2. Click Choose File and select the file to be analyzed.
3. Click Evaluate. The file uploads and evaluation results display. The following example shows the results for a compatible file: