Cascade
Worker lingua-cascade. One spoken turn through OpenRouter on https://inference.archangl.ai. IPv4: https://lingua-cascade.archangl.workers.dev.
lingua-cascade.archangl.workers.dev
Purpose
One spoken turn through OpenRouter on https://inference.archangl.ai.
Usage
POST /turn. Body is pcm16 at 16 kHz (16000). Send content-type: audio/pcm and x-lingua-sample-rate: 16000. A 200 returns pcm16 with x-lingua-transcript, x-lingua-reply, and x-lingua-sample-rate: 16000.
Worker lingua-voice reaches this engine through a Cloudflare service binding named CASCADE. Dummy host on that Request is cascade: POST https://cascade/turn. Harvest hang-up stays on worker lingua.
Stack
Same-account Workers AI binding: wrangler "ai": { "binding": "AI" }. Gateway https://inference.archangl.ai (slug inference). No AI_GATEWAY_TOKEN.
- STT
nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b- LLM
nvidia/nemotron-3-ultra-550b-a55b:free- TTS
deepgram/flux-tts:free·flux-alexis-en