Merge pull request #315 from pipecat-ai/aleix/stop-transcription-error

transports(daily): wait until start|stop_transcription are finished

CHANGELOG.md

@@ -11,6 +11,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 - STT services should be using ISO 8601 time format for transcription frames.
 
+- Fix an issue that would cause Daily transport to show a stop transcription
+  error when actually none occurred.
+
 ## [0.0.37] - 2024-07-22
 
 ### Added

src/pipecat/transports/services/daily.py

@@ -269,10 +269,7 @@ async def join(self):
                 logger.info(f"Joined {self._room_url}")
 
                 if self._token and self._params.transcription_enabled:
-                    logger.info(
-                        f"Enabling transcription with settings {self._params.transcription_settings}")
-                    self._client.start_transcription(
-                        self._params.transcription_settings.model_dump(exclude_none=True))
+                    await self._start_transcription()
 
                 await self._callbacks.on_joined(data["participants"]["local"])
             else:
@@ -284,6 +281,17 @@ async def join(self):
             logger.error(error_msg)
             await self._callbacks.on_error(error_msg)
 
+    async def _start_transcription(self):
+        future = self._loop.create_future()
+        logger.info(f"Enabling transcription with settings {self._params.transcription_settings}")
+        self._client.start_transcription(
+            settings=self._params.transcription_settings.model_dump(exclude_none=True),
+            completion=lambda error: future.set_result(error)
+        )
+        error = await future
+        if error:
+            logger.error(f"Unable to start transcription: {error}")
+
     async def _join(self):
         future = self._loop.create_future()
 
@@ -343,7 +351,7 @@ async def leave(self):
         logger.info(f"Leaving {self._room_url}")
 
         if self._params.transcription_enabled:
-            self._client.stop_transcription()
+            await self._stop_transcription()
 
         try:
             error = await self._leave()
@@ -360,6 +368,13 @@ async def leave(self):
             logger.error(error_msg)
             await self._callbacks.on_error(error_msg)
 
+    async def _stop_transcription(self):
+        future = self._loop.create_future()
+        self._client.stop_transcription(completion=lambda error: future.set_result(error))
+        error = await future
+        if error:
+            logger.error(f"Unable to stop transcription: {error}")
+
     async def _leave(self):
         future = self._loop.create_future()