Since we introduced the built-in capabilities for Speech-to-Text transcription and PII detection in our 22.10 release, we have embarked on a journey to offer you smarter, faster, and easier AI tools—and today, we are thrilled to announce a new addition to speech-to-text recognition: Support for multimodel, yet another feature to further enhance the OCI speech services.
Imagine being able to transcribe not just the speech, but in over 50 languages. Siebel now supports Whisper, a speech-to-text model from OpenAI, in addition to the OCI speech model. Whisper supports file-based voice-to-text transcription for over 50 languages.
What’s New?
Trained on a large corpus of multilingual data collected from the web, the Whisper model offers a suite of features and benefits:
- Multilingual support: Whisper’s multilingual support includes, Arabic, Armenian, Azerbaijani, Belarusian, Bosnian, Bulgarian, Catalan, Chinese, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, Galician, German, Greek, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Kannada, Kazakh, Korean, Latvian, Lithuanian, Macedonian, Malay, Marathi, Māori, Nepali, Norwegian, Persian, Polish, Portuguese, Romanian, Russian, Serbian, Slovak, Slovenian, Spanish, Swahili, Swedish, Tagalog, Tamil, Thai, Turkish, Ukrainian, Urdu, Vietnamese, and Welsh, allowing you to transcribe your audio files in your preferred language.
- Seamless integration: Whisper model uses the same service end points and SDK interfaces as the OCI Speech model to give you flexibility and compatibility.
- Diarization for Speaker labeling: The Whisper model uses diarization to automatically tag different speakers in your transcriptions to keep things clear and organized.
What’s the Best Model?
No more worrying about the multilingual support. With the Whisper model, you’ll get more reliable transcriptions and that too in many languages. It’s perfect for anyone looking to enhance their transcription workflow with a seamless, AI-powered solution.
Navigating the choice between the OCI speech and Whisper models involves involves evaluating the use cases and specific requirements. Each use case may need a different type of model to achieve the desired results.
We are committed to help you choose the suitable model by comparing and weighing models against your criteria. Contact your Oracle representative to discuss how AI can help you unlock the value of your multimedia data.
For more information on AI for Siebel CRM, refer to Artificial Intelligence (AI) Services for Siebel CRM.