Thanks so much for reaching out! I wanted to share that LiveKit's integration with Amazon Transcribe doesn't currently support passing custom machine learning models directly. But don’t worry—there are some great features within AWS Transcribe that can help you out, such as: • Custom Vocabularies: These let you boost transcription accuracy by adding domain-specific terms that matter most to you. • Vocabulary Filters: You can use these to remove, mask, or flag any sensitive or unwanted words, keeping your transcriptions just right. If you’re looking for more advanced customization, you might want to explore Deepgram, which offers fine-tuning and customizable speech models. Alternatively, you could also consider integrating directly with AWS Transcribe’s API outside of LiveKit to use custom models. Please feel free to reach out if you want to chat more about these options or need any help—I’m here for you! Sources: Amazon Transcribe STT integration guide | LiveKit Docs | Deepgram STT integration guide | LiveKit Docs | Deepgram STT integration guide | LiveKit Docs | Speech-to-text (STT) integrations | LiveKit Docs | AWS AI and LiveKit | LiveKit Docs