Transcription: config-driven OpenAI-compatible STT with OpenAI fallback (server-26#297, server-26#83)

STT_PROVIDER=auto picks Groq whisper-large-v3-turbo only when GROQ_API_KEY is
set (else OpenAI, unchanged); compat covers any OpenAI-compatible server via
STT_BASE_URL/STT_API_KEY. A failed primary falls back to OpenAI STT_MODEL on
the same downloaded audio; the fallback reports to its own ai_health tier so
a dead primary stays red. The non-OpenAI provider gets a token-budgeted
glossary prompt (area places, local_knowledge, vocabulary; never ten-codes),
guarded by a narrow prompt-echo check. A per-30s-window zlib compression
check (Whisper's 2.4) adds a noise gate that survives correction being off
(#83, partial). Call docs record stt_provider/model/audio_seconds/confidence.
The sweep hold-back counts the fallback attempt. gate_chatter added to
chatter_classifier (used by transcription to skip correction when
CHATTER_GATE_ENABLED). GROQ_API_KEY templated with default ''.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

infra/ansible/roles/deploy/templates/c2-core.env.j2

@@ -26,6 +26,10 @@ PUBLIC_API_URL=https://api.{{ domain }}
 OPENAI_API_KEY={{ vault_openai_api_key }}
 GOOGLE_MAPS_API_KEY={{ vault_google_maps_api_key }}
 GEMINI_API_KEY={{ vault_gemini_api_key }}
+# STT provider (server-26#297). With this set, STT_PROVIDER=auto moves
+# transcription to Groq whisper-large-v3-turbo with OpenAI as the fallback;
+# default('') keeps a vault that predates the key on OpenAI, unchanged.
+GROQ_API_KEY={{ vault_groq_api_key | default('') }}
 
 SERVICE_KEY={{ vault_service_key }}
 ENROLLMENT_TOKEN={{ vault_enrollment_token }}