aria-audio / README.md
Malina
Claude Fable 5
ARIA Audio: MMS-TTS (pol/eng) + wav2vec2 emotion service
eaa9bb7
|
Raw History Blame Contribute Delete
710 Bytes
---
title: ARIA Audio
emoji: πŸ”Š
colorFrom: purple
colorTo: blue
sdk: docker
app_port: 7860
pinned: false
license: apache-2.0
short_description: MMS-TTS (pol/eng) + voice emotion for ARIA AGENT
---
# ARIA Audio
Tiny FastAPI service backing the **ARIA AGENT** app for the models that no
serverless inference provider hosts:
- `POST /tts` `{"text": "...", "lang": "pol" | "eng"}` β†’ `audio/wav`
(facebook/mms-tts-pol / facebook/mms-tts-eng)
- `POST /emotion` (body: 16 kHz mono WAV) β†’ `[{"label","score"}, ...]`
(superb/wav2vec2-base-superb-er)
- `GET /` β†’ health
Models load lazily on first use and stay warm. CPU-basic is enough β€”
MMS is a 36M-param VITS and the classifier is a base wav2vec2.