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

Fix ElevenLabs TTS word timestamp interleaving across sentences

Browse Source 
Move cumulative_time and partial word state resets from every run_tts
call into the new-context creation block. With the multi-stream WebSocket
API, multiple sentences share the same context, so resetting timing state
on each run_tts call caused sentences to get overlapping timestamps,
resulting in interleaved word ordering.
This commit is contained in:
Mark Backman
2026-02-12 08:57:02 -05:00
parent d99a256715
commit 7850517ba4
1 changed files with 6 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
src/pipecat/services/elevenlabs/tts.py
View File

@@ -700,9 +700,6 @@ class ElevenLabsTTSService(AudioContextWordTTSService):
try: try:
await self.start_ttfb_metrics() await self.start_ttfb_metrics()
yield TTSStartedFrame(context_id=context_id) yield TTSStartedFrame(context_id=context_id)
self._cumulative_time = 0
self._partial_word = ""
self._partial_word_start_time = 0.0
# If a context ID does not exist, use the provided one. # If a context ID does not exist, use the provided one.
# If an ID exists, that means the Pipeline doesn't allow # If an ID exists, that means the Pipeline doesn't allow
# user interruptions, so continue using the current ID. # user interruptions, so continue using the current ID.
@@ -710,6 +707,12 @@ class ElevenLabsTTSService(AudioContextWordTTSService):
# an interruption, which resets the context ID. # an interruption, which resets the context ID.
if not self._context_id: if not self._context_id:
self._context_id = context_id self._context_id = context_id
# Reset timing state only when starting a new context.
# Within a context, cumulative_time must accumulate across
# sentences so word timestamps are properly sequenced.
self._cumulative_time = 0
self._partial_word = ""
self._partial_word_start_time = 0.0
if not self.audio_context_available(self._context_id): if not self.audio_context_available(self._context_id):
await self.create_audio_context(self._context_id) await self.create_audio_context(self._context_id)