christian/matrix-ai-agent
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(voice): separate aiohttp sessions for STT and TTS

Browse Source 
Sharing one session between ElevenLabs STT (WebSocket) and TTS (HTTP)
can cause connection conflicts. Use dedicated sessions for each.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Christian Gick
2026-02-22 11:15:46 +02:00
parent 475ab38f6f
commit f74a11fde8
1 changed files with 4 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
voice.py
View File

@@ -113,6 +113,7 @@ class VoiceSession:
self.session = None self.session = None
self._task = None self._task = None
self._http_session = None self._http_session = None
self._stt_session = None
self._caller_key: bytes | None = None self._caller_key: bytes | None = None
self._caller_identity: str | None = None self._caller_identity: str | None = None
self._caller_all_keys: dict = {} # {index: bytes} — all caller keys by index self._caller_all_keys: dict = {} # {index: bytes} — all caller keys by index
@@ -196,7 +197,7 @@ class VoiceSession:
self._task = asyncio.create_task(self._run()) self._task = asyncio.create_task(self._run())
async def stop(self): async def stop(self):
for obj in [self.session, self.lk_room, self._http_session]: for obj in [self.session, self.lk_room, self._http_session, self._stt_session]:
if obj: if obj:
try: try:
if hasattr(obj, "aclose"): if hasattr(obj, "aclose"):
@@ -344,9 +345,10 @@ class VoiceSession:
# Voice pipeline — George (British male, multilingual DE/EN) # Voice pipeline — George (British male, multilingual DE/EN)
self._http_session = aiohttp.ClientSession() self._http_session = aiohttp.ClientSession()
self._stt_session = aiohttp.ClientSession() # separate session avoids WS/HTTP conflicts
voice_id = os.environ.get("ELEVENLABS_VOICE_ID", DEFAULT_VOICE_ID) voice_id = os.environ.get("ELEVENLABS_VOICE_ID", DEFAULT_VOICE_ID)
self.session = AgentSession( self.session = AgentSession(
stt=elevenlabs.STT(api_key=ELEVENLABS_KEY, http_session=self._http_session), stt=elevenlabs.STT(api_key=ELEVENLABS_KEY, http_session=self._stt_session),
llm=lk_openai.LLM(base_url=LITELLM_URL, api_key=LITELLM_KEY, model=self.model), llm=lk_openai.LLM(base_url=LITELLM_URL, api_key=LITELLM_KEY, model=self.model),
tts=elevenlabs.TTS(voice_id=voice_id, model="eleven_multilingual_v2", tts=elevenlabs.TTS(voice_id=voice_id, model="eleven_multilingual_v2",
api_key=ELEVENLABS_KEY, http_session=self._http_session), api_key=ELEVENLABS_KEY, http_session=self._http_session),