Add Tinfoil audio models (whisper STT, voxtral-tts) for voice mode + API use

config.yaml

@@ -96,6 +96,32 @@ model_list:
       input_cost_per_token: 0.0000011
       output_cost_per_token: 0.0000044
 
+  # --- Audio models (Tinfoil, inside the TEE) ---
+  # NOT chat models: these power /v1/audio/* routes (STT for dictation, TTS for
+  # voice mode). They stay VISIBLE in the API model list so developer members
+  # can call them, but the portal filters them out of the chat-facing list
+  # (Open WebUI) by their `mode` field, so they never appear as pickable chat
+  # options. Pricing per Tinfoil catalog: whisper $0.05/1M in; voxtral-tts
+  # listed $0/$0 (verify on invoice — may be beta-free).
+  - model_name: tinfoil/whisper-large-v3-turbo
+    litellm_params:
+      model: audio_transcription/whisper-large-v3-turbo
+      api_base: http://127.0.0.1:3301/v1
+      api_key: os.environ/TINFOIL_API_KEY
+    model_info:
+      mode: audio_transcription
+      input_cost_per_token: 0.00000005
+
+  - model_name: tinfoil/voxtral-tts
+    litellm_params:
+      model: audio_speech/voxtral-tts
+      api_base: http://127.0.0.1:3301/v1
+      api_key: os.environ/TINFOIL_API_KEY
+    model_info:
+      mode: audio_speech
+      input_cost_per_token: 0.0
+      output_cost_per_token: 0.0
+
   # --- PublicAI (publicly developed / sovereign models) ---
   # OpenAI-compatible gateway for public open models. Apertus is the Swiss AI
   # Initiative's fully-open model (Apache-2.0: weights, code, and training data).
@@ -120,6 +146,32 @@ model_list:
       input_cost_per_token: 0.00000082
       output_cost_per_token: 0.00000292
 
+  # --- Audio models (Tinfoil, in-TEE) ---
+  # Used for chat dictation (STT) and voice mode (TTS). These are NOT chat
+  # models: the member portal's /v1/models filters them out of the chat model
+  # list (see AUDIO_MODEL_PREFIXES there) so members don't see them in the
+  # picker, but they remain fully callable via /v1/audio/* for API users.
+  # whisper-large-v3-turbo: $0.05/1M input tokens. voxtral-tts: listed $0/$0.
+  # NOTE: LiteLLM routes audio by the openai/ provider + the endpoint called
+  # (/v1/audio/transcriptions or /v1/audio/speech) — there is no
+  # "audio_transcription/" provider prefix.
+  - model_name: tinfoil/whisper-large-v3-turbo
+    litellm_params:
+      model: openai/whisper-large-v3-turbo
+      api_base: http://127.0.0.1:3301/v1
+      api_key: os.environ/TINFOIL_API_KEY
+    model_info:
+      mode: audio_transcription
+      input_cost_per_token: 0.00000005
+
+  - model_name: tinfoil/voxtral-tts
+    litellm_params:
+      model: openai/voxtral-tts
+      api_base: http://127.0.0.1:3301/v1
+      api_key: os.environ/TINFOIL_API_KEY
+    model_info:
+      mode: audio_speech
+
 # Fallback: if DeepSeek is down, use GPT-OSS
 # NOTE: DeepSeek V4.1 Flash is a reasoning model — generations routinely run
 # longer than 30s. A 30s timeout caused LiteLLM to abandon in-flight DeepSeek