vh/esh-pfi-infrastructure
1
0
Fork 0
Code Issues 7 Pull Requests Actions Packages Projects Releases Wiki Activity

catalog: promote chatterbox-fast to ready; vibevoice->down; resolve voxtral 8197 collision

Browse Source 
- chatterbox-fast experimental -> ready: browser audition verified end-to-end
  (operator confirmed progressive playback "excellent" 2026-06-02).
- vibevoice ready -> down: no container running on irv-ml1 (connection refused);
  catalog status was stale.
- voxtral: NOT a stale typo — its stack genuinely claimed :8197, the port now held
  by the live chatterbox-fast. voxtral is down, so moved IT to :8201 (catalog
  endpoint + source_url, stacks/voxtral/.env.example + README, host .env) rather
  than disturb the live service. No live clash existed (voxtral down) but it was a
  latent deploy-time collision I introduced by placing chatterbox-fast on 8197.

No catalog_version bump (status changes + endpoint correction, additive). Validates
against the schema.
This commit is contained in:
vh
2026-06-02 09:10:57 -07:00
parent fa56718ba0
commit 099e1d7418
3 changed files with 14 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
stacks/voxtral/.env.example
+3 -1
View File
@@ -15,7 +15,9 @@ VOXTRAL_MODEL=mistralai/Voxtral-4B-TTS-2603
# ── network ──────────────────────────────────────────────────────────
# Host port (container listens on 8000 internally).
VOXTRAL_PORT=8197
# Was 8197 — moved to 8201 (2026-06-02): 8197 is taken by the live
# chatterbox-fast stack. Don't reuse 8197.
VOXTRAL_PORT=8201
VOXTRAL_BIND=0.0.0.0
# ── runtime / GPU ────────────────────────────────────────────────────
stacks/voxtral/README.md
+5 -5
View File
@@ -43,24 +43,24 @@ English; nothing else is multilingual at all).
## API
vLLM-Omni serves an OpenAI-compatible API at
`http://10.100.79.3:8197/v1`:
`http://10.100.79.3:8201/v1`:
```bash
# Single-shot synthesis.
curl -fsS -X POST http://10.100.79.3:8197/v1/audio/speech \
curl -fsS -X POST http://10.100.79.3:8201/v1/audio/speech \
-H 'Content-Type: application/json' \
-d '{"model":"mistralai/Voxtral-4B-TTS-2603","input":"Hello there.","voice":"alloy","response_format":"wav"}' \
> out.wav
# Streaming.
curl -fsS -X POST http://10.100.79.3:8197/v1/audio/speech \
curl -fsS -X POST http://10.100.79.3:8201/v1/audio/speech \
-H 'Content-Type: application/json' \
-d '{"model":"mistralai/Voxtral-4B-TTS-2603","input":"long passage…","voice":"alloy","stream":true}' \
| mpv --no-cache -
# vLLM-Omni standard endpoints.
curl http://10.100.79.3:8197/v1/models # confirms model loaded
curl http://10.100.79.3:8197/v1/audio/voices # built-in + cloned voices
curl http://10.100.79.3:8201/v1/models # confirms model loaded
curl http://10.100.79.3:8201/v1/audio/voices # built-in + cloned voices
```
## Deploy