wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

services(cartesia): generated TTSStoppedFrame after no more audio

Browse Source 
The TTSStoppedFrame should be generated when the TTS services stoped generating
audio not when the bot stops speaking.
This commit is contained in:
Aleix Conchillo Flaqué
2024-11-10 09:55:45 +01:00
parent 446bb0aeaf
commit d125a38737
1 changed files with 2 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
src/pipecat/services/cartesia.py
View File

@@ -228,14 +228,13 @@ class CartesiaTTSService(WordTTSService):
if not msg or msg["context_id"] != self._context_id:
continue
if msg["type"] == "done":
await self.push_frame(TTSStoppedFrame())
await self.stop_ttfb_metrics()
# Unset _context_id but not the _context_id_start_timestamp
# because we are likely still playing out audio and need the
# timestamp to set send context frames.
self._context_id = None
await self.add_word_timestamps(
[("TTSStoppedFrame", 0), ("LLMFullResponseEndFrame", 0), ("Reset", 0)]
)
await self.add_word_timestamps([("LLMFullResponseEndFrame", 0), ("Reset", 0)])
elif msg["type"] == "timestamps":
await self.add_word_timestamps(
list(zip(msg["word_timestamps"]["words"], msg["word_timestamps"]["start"]))