fix(telegram): separate voice transcription client (#166)

docs/how-to/voice-notes.md

@@ -9,6 +9,10 @@ Enable transcription so voice notes become normal text runs.
     ```sh
     takopi config set transports.telegram.voice_transcription true
     takopi config set transports.telegram.voice_transcription_model "gpt-4o-mini-transcribe"
+
+    # local OpenAI-compatible transcription server (optional)
+    takopi config set transports.telegram.voice_transcription_base_url "http://localhost:8000/v1"
+    takopi config set transports.telegram.voice_transcription_api_key "local"
     ```
 
 === "toml"
@@ -17,13 +21,17 @@ Enable transcription so voice notes become normal text runs.
     [transports.telegram]
     voice_transcription = true
     voice_transcription_model = "gpt-4o-mini-transcribe" # optional
+    voice_transcription_base_url = "http://localhost:8000/v1" # optional
+    voice_transcription_api_key = "local" # optional
     ```
 
-Set `OPENAI_API_KEY` in your environment (uses OpenAI’s transcription API).
+Set `OPENAI_API_KEY` in your environment (or `voice_transcription_api_key` in config).
 
-To use a local OpenAI-compatible Whisper server, also set `OPENAI_BASE_URL`
-(for example, `http://localhost:8000/v1`) and a dummy `OPENAI_API_KEY` if your server ignores it.
-If your server requires a specific model name, set `voice_transcription_model` (for example, `whisper-1`).
+To use a local OpenAI-compatible Whisper server, set `voice_transcription_base_url`
+(and `voice_transcription_api_key` if the server expects one). This keeps engine
+requests on their own base URL without relying on `OPENAI_BASE_URL`. If your server
+requires a specific model name, set `voice_transcription_model` (for example,
+`whisper-1`).
 
 ## Behavior