docs: improved tts usage docs

Author: ErikBjare

gptme/tools/tts.py

@@ -3,12 +3,27 @@
 
 Uses Kokoro for local TTS generation.
 
-Note:
-    To use this tool, you also need run the Kokoro TTS server: ``./scripts/tts_server.py``
+.. rubric:: Usage
 
-Environment Variables:
-    GPTME_TTS_VOICE: Set the voice to use for TTS. Available voices depend on the TTS server.
-    GPTME_VOICE_FINISH: If set to "true" or "1", waits for speech to finish before exiting. This is useful when you want to ensure the full message is spoken.
+.. code-block:: bash
+
+    # Install gptme with TTS extras
+    pipx install gptme[tts]
+
+    # Clone gptme repository
+    git clone https://github.com/gptme/gptme.git
+    cd gptme
+
+    # Run the Kokoro TTS server (needs uv installed)
+    ./scripts/tts_server.py
+
+    # Start gptme (should detect the running TTS server)
+    gptme 'hello, testing tts'
+
+.. rubric:: Environment Variables
+
+- ``GPTME_TTS_VOICE``: Set the voice to use for TTS. Available voices depend on the TTS server.
+- ``GPTME_VOICE_FINISH``: If set to "true" or "1", waits for speech to finish before exiting. This is useful when you want to ensure the full message is spoken.
 """
 
 import io