Add Hosted API (Trelis Router) section

README.md

@@ -12,7 +12,18 @@ pinned: false
 
 Upload audio of two people talking (possibly overlapping) and get separate transcripts for each speaker with timestamps.
 
-Running on CPU — expect ~30-60s per 30s of audio.
+This Space runs on CPU (~30–60s per 30s of audio). For production use, Chorus is also available as a **hosted GPU API** — see below.
+
+## Hosted API (Trelis Router)
+
+Chorus is available as a hosted GPU endpoint on [Trelis Router](https://router.trelis.com) — handles long audio end-to-end (VAD chunking + cross-chunk speaker clustering). Model id `trelis/chorus-v1`, base URL `https://router.trelis.com/api/v1`.
+
+```bash
+curl -X POST https://router.trelis.com/api/v1/transcribe \
+  -H "Authorization: Bearer $TRELIS_ROUTER_API_KEY" \
+  -F model=trelis/chorus-v1 \
+  -F file=@meeting.wav
+```
 
 ## How it works
 
@@ -26,7 +37,7 @@ See the [Trelis Studio repo](https://github.com/TrelisResearch/studio) (private)
 
 ## Model
 
-- **Chorus Turbo**: `Trelis/chorus-merged-test` — merged standalone Whisper model (base + LoRA merged + expanded tokenizer)
+- **Chorus v1**: [`Trelis/Chorus-v1`](https://huggingface.co/Trelis/Chorus-v1) — merged standalone Whisper model (base + LoRA merged + expanded tokenizer)
 
 ## Environment