What it is and what it is for
Media AI combines three tools: Voice Studio turns text into speech and audio into text. Translate Studio translates texts. Image Studio creates and analyzes images. All features are paid features. Translate Studio translates text, Excel/CSV and JSON, but not PDF documents.
How it works
- Open Media AI → Voice Studio. Choose Text to speech (TTS), enter text, pick language and voice and click Generate audio. Then click Download.
- For a transcript, choose Speech to text (STT) and upload an audio or video file.
- Open Media AI → Translate Studio, choose Text, Excel or JSON and click Translate.
- Open Media AI → Image Studio and choose Generate image, Analyze image or Remove background.
- A document as an audiobook: Documents → select the document → Actions → Agents & workflows → Summarize document. Choose PDF summary, Podcast audiobook or PDF and podcast and click Start summary.
Good to know
- Voice Studio has the models Basic, Premium and Ultra. Voice cloning and WAV and OGG are available from Premium.
- For transcripts, only Ultra separates several speakers.
- Generated audio can only be downloaded for a limited time. You can file images with Save to Document AI.
- The audiobook and summary are saved as a new document in the workspace. The document needs recognized text.