CartesiaTTSService: reset context id when flushing audio

2025-02-11 23:36:08 -08:00
2 changed files with 4 additions and 0 deletions
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -52,6 +52,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0

 ### Fixed

+- Fixed a `CartesiaTTSService` issue that could cause audio overlapping in some
+  cases.
+
 - Fixed an issue that was causing `AudioBufferProcessor` to not record
  synchronized audio.

--- a/src/pipecat/services/cartesia.py
+++ b/src/pipecat/services/cartesia.py
@@ -239,6 +239,7 @@ class CartesiaTTSService(WordTTSService, WebsocketService):
        logger.trace(f"{self}: flushing audio")
        msg = self._build_msg(text="", continue_transcript=False)
        await self._websocket.send(msg)
+        self._context_id = None

    async def _receive_messages(self):
        async for message in self._get_websocket():