feat: add deepgram audio options

docs/nodes/audio.md

@@ -80,6 +80,7 @@ read_when:
 - Provider auth follows the standard model auth order (auth profiles, env vars, `models.providers.*.apiKey`).
 - Deepgram picks up `DEEPGRAM_API_KEY` when `provider: "deepgram"` is used.
 - Deepgram setup details: [Deepgram (audio transcription)](/providers/deepgram).
+- Audio providers can override `baseUrl`/`headers` via `tools.media.audio`.
 - Default size cap is 20MB (`tools.media.audio.maxBytes`). Oversize audio is skipped for that model and the next entry is tried.
 - Default `maxChars` for audio is **unset** (full transcript). Set `tools.media.audio.maxChars` or per-entry `maxChars` to trim output.
 - Use `tools.media.audio.attachments` to process multiple voice notes (`mode: "all"` + `maxAttachments`).

docs/nodes/media-understanding.md

@@ -32,6 +32,8 @@ If understanding fails or is disabled, **the reply flow continues** with the ori
 - `tools.media.models`: shared model list (use `capabilities` to gate).
 - `tools.media.image` / `tools.media.audio` / `tools.media.video`:
   - defaults (`prompt`, `maxChars`, `maxBytes`, `timeoutSeconds`, `language`)
+  - provider overrides (`baseUrl`, `headers`)
+  - Deepgram audio options (`deepgram` in `tools.media.audio`)
   - optional **per‑capability `models` list** (preferred before shared models)
   - `attachments` policy (`mode`, `maxAttachments`, `prefer`)
   - `scope` (optional gating by channel/chatType/session key)

docs/providers/deepgram.md

@@ -41,6 +41,9 @@ DEEPGRAM_API_KEY=dg_...
 
 - `model`: Deepgram model id (default: `nova-3`)
 - `language`: language hint (optional)
+- `tools.media.audio.deepgram.detectLanguage`: enable language detection (optional)
+- `tools.media.audio.deepgram.punctuate`: enable punctuation (optional)
+- `tools.media.audio.deepgram.smartFormat`: enable smart formatting (optional)
 
 Example with language:
 ```json5
@@ -58,7 +61,27 @@ Example with language:
 }
 ```
 
+Example with Deepgram options:
+```json5
+{
+  tools: {
+    media: {
+      audio: {
+        enabled: true,
+        deepgram: {
+          detectLanguage: true,
+          punctuate: true,
+          smartFormat: true
+        },
+        models: [{ provider: "deepgram", model: "nova-3" }]
+      }
+    }
+  }
+}
+```
+
 ## Notes
 
 - Authentication follows the standard provider auth order; `DEEPGRAM_API_KEY` is the simplest path.
+- Override endpoints or headers with `tools.media.audio.baseUrl` and `tools.media.audio.headers` when using a proxy.
 - Output follows the same audio rules as other providers (size caps, timeouts, transcript injection).