Phoenix currently supports displaying images in LLM traces, but there is no documentation or example showing support for viewing audio samples directly in the trace UI. The official multimodal tracing guide and related documentation only mention images, not audio files or previews in traces. Audio support is mentioned for embeddings and evals, but not for trace visualization in the UI (multimodal tracing docs, audio support PR).If you need to view audio in traces, this feature is not currently documented or supported in the UI. Would you like more detail on audio support in other Phoenix features, such as evals?Sources:
- Multimodal Tracing Docs
- Audio Support PR
馃挕聽Hint: Mention RunLLM in the thread for followups.