Photo Avatar in Azure AI Speech is now generally available in standard and custom flavors. Standard Photo Avatar produces a talking head video from a single photo at 512x512 resolution, and custom Photo Avatar lets you fine-tune the look from your own image with one minute of consent audio for the matching voice. Both modes run through the same batch synthesis and real-time synthesis APIs already used for video avatars, so existing avatar code paths keep working. Photo Avatar is built on the VASA-1 model family and integrates with Voice Live for low-latency, two-way conversational scenarios where you need a face on the agent.
Learn more.