| Document Number | Revision Number | Revision Date |
|---|---|---|
| KN. GU.25.EN | Rev23 | 30.05.2025 |
| Feature | Description |
|---|---|
| Custom Word | Knovvu SR offers users the ability to request the addition of custom words that are currently not included in the language model. Information about the conditions can be obtained from the consultant. |
| Global Vocabulary | Knovvu SR supports 34 languages. |
| Supported Audio Formats | Knovvu SR uses ffmpeg to convert audio files. Main supported formats are G729, Mp3, Mp4, Wav and Opus. |
| Online Speech Recognition | Knovvu SR provides real-time recognition. |
| Covering Different Accents | Knovvu SR covers many different accents for a language in one model, so customers do not need to use different language models for different accents. |
| Masking | Knovvu SR provides masking to recognition results with defining regex rules. |
| Mixed-Models | Knovvu SR provides multi and bilingual language models that can leverage the knowledge from multiple languages to enhance speech recognition accuracy. |
Transcription Features
Knovvu SR offers a wide range of options and features to suit your needs. Click to learn how.