Speech calls keep one connection per server, opened when listening starts

transcribe and speak share an httpx client per speech server with a 300 s
keep-alive, and run on the engine's loop. stt warms it with GET /v1/models
when an utterance opens, so a reply's first sentence finds the connection
open: a new one over a lossy link cost up to a second (openpanel V4).
This commit is contained in:
Melvin Strobl
2026-10-19 22:06:08 +02:00
parent f50d8b9570
commit 4df7bdb057
4 changed files with 67 additions and 26 deletions
+31 -16
View File
@@ -160,6 +160,26 @@ async def list_models(api_base: str, api_key: str, timeout: float = 15.0) -> lis
return sorted(str(m["id"]) for m in data if isinstance(m, dict) and "id" in m)
#: One client per speech server, so its connection stays open between calls
#: (`parrot serve` keeps an idle one 600 s). A new connection over a lossy
#: link can cost a second, which a spoken reply cannot spare.
_speech: dict[str, httpx.AsyncClient] = {}
def _speech_client(api_base: str) -> httpx.AsyncClient:
"""The client for this speech server. Used from the engine's loop only."""
http = _speech.get(api_base)
if http is None:
limits = httpx.Limits(keepalive_expiry=300)
http = _speech[api_base] = httpx.AsyncClient(limits=limits)
return http
async def warm(api_base: str) -> None:
"""Open the connection to a speech server ahead of the call that needs it."""
await _speech_client(api_base).get(api_base.rstrip("/") + "/models", timeout=10)
async def transcribe(
api_base: str,
audio: bytes,
@@ -170,12 +190,12 @@ async def transcribe(
timeout: float = 30.0,
) -> str:
"""``POST {api_base}/audio/transcriptions``: a whole clip, and what it says."""
async with httpx.AsyncClient(timeout=timeout) as http:
response = await http.post(
api_base.rstrip("/") + "/audio/transcriptions",
files={"file": (filename, audio, media_type)},
data={"model": model, "response_format": "json"},
)
response = await _speech_client(api_base).post(
api_base.rstrip("/") + "/audio/transcriptions",
files={"file": (filename, audio, media_type)},
data={"model": model, "response_format": "json"},
timeout=timeout,
)
if response.is_error:
raise ProviderError(_detail(response))
return str(response.json().get("text") or "")
@@ -194,16 +214,11 @@ async def speak(
MP3 rather than WAV: a seventh of the bytes, which over a slow link to
the server is most of the wait for a sentence.
"""
async with httpx.AsyncClient(timeout=timeout) as http:
response = await http.post(
api_base.rstrip("/") + "/audio/speech",
json={
"model": model,
"input": text,
"voice": voice,
"response_format": "mp3",
},
)
response = await _speech_client(api_base).post(
api_base.rstrip("/") + "/audio/speech",
json={"model": model, "input": text, "voice": voice, "response_format": "mp3"},
timeout=timeout,
)
if response.is_error:
raise ProviderError(_detail(response))
return response.content