From 34ce3b6753c0bb7021b5a8473a1c560d248d6019 Mon Sep 17 00:00:00 2001
From: inference-bot <bot@inference.coop>
Date: Sun, 27 Sep 2026 11:25:50 -0600
Subject: [PATCH] Document audio models (STT/TTS) with API examples

---
 models.md | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

diff --git a/models.md b/models.md
index 3c4e240..1c7d15e 100644
--- a/models.md
+++ b/models.md
@@ -52,6 +52,38 @@ provider — your own cost is your monthly allowance, not per-token billing).
 | `publicai/apertus-v1.5-8b` | PublicAI | policy | undisclosed | $0.10 / $0.20 | Fully open sovereign model, small/fast. |
 | `publicai/apertus-v1.5-70b` | PublicAI | policy | undisclosed | $0.82 / $2.92 | Fully open sovereign model, large/capable. |
 
+### Audio models
+
+These are **not chat models** — they power the chat's voice mode (dictation
+and spoken replies) and are available through the API on `/v1/audio/*` routes
+for members building speech into their own tools. They're hidden from the chat
+model picker to avoid confusion.
+
+| Model | Provider | Use | Pricing |
+|---|---|---|---|
+| `tinfoil/whisper-large-v3-turbo` | Tinfoil | Speech-to-text | $0.05 / 1M input tokens |
+| `tinfoil/voxtral-tts` | Tinfoil | Text-to-speech | listed $0 (verify on invoice) |
+
+Both run inside Tinfoil's enclaves, so voice data gets the same architectural
+privacy as the private chat models. TTS voices available: `neutral_female`,
+`neutral_male`, `casual_female/male`, `cheerful_female`, plus French, German,
+Spanish, Italian, Portuguese, Dutch, and Hindi variants.
+
+```bash
+# Speech-to-text
+curl https://gateway.inference.coop/v1/audio/transcriptions \
+  -H "Authorization: Bearer sk-your-key" \
+  -F file=@your-audio.mp3 \
+  -F model=tinfoil/whisper-large-v3-turbo
+
+# Text-to-speech (returns WAV audio)
+curl https://gateway.inference.coop/v1/audio/speech \
+  -H "Authorization: Bearer sk-your-key" \
+  -H "Content-Type: application/json" \
+  -d '{"model": "tinfoil/voxtral-tts", "input": "Hello from the co-op", "voice": "neutral_female"}' \
+  --output speech.wav
+```
+
 ### About the Apertus models
 
 Apertus is the **Swiss AI Initiative's** open foundation model, built by a