The platform supports various audio functions:
Voice input: You can enter spoken language directly into the chat via the microphone. The speech is automatically converted into text.
Upload audio files: You can upload audio and video files. The limit is 30 MB. The files are automatically transcribed and made available to the AI models as text.
Retrieve transcript: Click on an uploaded audio/video file in the chat. You can view and copy the transcribed text.
Text-to-speech (restrictions): The read-aloud function for chat content currently works best for English texts. German texts may be pronounced unnaturally, as the language model used is primarily optimized for other languages.