Merge pull request #2296 from pipecat-ai/mb/switch-rime-voices

Added the ability to switch voices to RimeTTSService

CHANGELOG.md

@@ -13,7 +13,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   A video service that handles audio streaming and requests HeyGen to generate
   avatar video responses. (see https://www.heygen.com/)
 
+- Added the ability to switch voices to `RimeTTSService`.
+
 - Added Async.ai TTS integration (https://async.ai/)
+
   - `AsyncAITTSService` – WebSocket-based streaming TTS with interruption support
   - `AsyncAIHttpTTSService` – HTTP-based streaming TTS service
   - Example scripts:

src/pipecat/services/rime/tts.py

@@ -13,7 +13,7 @@ using Rime's API for streaming and batch audio synthesis.
 import base64
 import json
 import uuid
-from typing import AsyncGenerator, Optional
+from typing import Any, AsyncGenerator, Mapping, Optional
 
 import aiohttp
 from loguru import logger
@@ -181,6 +181,16 @@ class RimeTTSService(AudioContextWordTTSService):
         self._model = model
         await super().set_model(model)
 
+    async def _update_settings(self, settings: Mapping[str, Any]):
+        """Update service settings and reconnect if voice changed."""
+        prev_voice = self._voice_id
+        await super()._update_settings(settings)
+        if not prev_voice == self._voice_id:
+            self._settings["speaker"] = self._voice_id
+            logger.info(f"Switching TTS voice to: [{self._voice_id}]")
+            await self._disconnect()
+            await self._connect()
+
     def _build_msg(self, text: str = "") -> dict:
         """Build JSON message for Rime API."""
         return {"text": text, "contextId": self._context_id}