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
+16 -5
View File
@@ -9,6 +9,7 @@ it gets.
from __future__ import annotations
import asyncio
import contextlib
import hashlib
import logging
import re
@@ -128,6 +129,13 @@ class _Speech(Node):
def _load(self, reference: dict[str, Any]) -> bytes:
return b"".join(self._artifacts.read(str(reference["digest"])))
def _call(self, work: Coroutine[Any, Any, Any]) -> Future[Any]:
"""Run on the engine's loop, where the server's connection is kept."""
if self._loop is None:
work.close()
raise RuntimeError(f"{self.name} only runs in a live flow")
return asyncio.run_coroutine_threadsafe(work, self._loop)
def _say(self, **values: Any) -> None:
"""Publish on the ports that are wired."""
wired = {spec.port for spec in self.output_ports if spec.name}
@@ -231,18 +239,21 @@ class SttNode(_Speech):
def _spawn(self, work: Coroutine[Any, Any, None]) -> None:
"""Run on the engine's loop, so this run can return at once."""
if self._loop is None:
work.close()
raise RuntimeError("stt only hears in a live flow")
task = asyncio.run_coroutine_threadsafe(work, self._loop)
task = self._call(work)
self._tasks.add(task)
task.add_done_callback(self._tasks.discard)
def _open(self, url: str) -> asyncio.Queue[bytes | None]:
chunks: asyncio.Queue[bytes | None] = asyncio.Queue()
self._spawn(self._transcribe(url, chunks))
# The reply's first sentence then finds the connection open.
self._spawn(self._warm(url))
return chunks
async def _warm(self, url: str) -> None:
with contextlib.suppress(Exception):
await client.warm(url + "/v1")
def _feed(self, chunks: asyncio.Queue[bytes | None], chunk: bytes | None) -> None:
assert self._loop is not None
self._loop.call_soon_threadsafe(chunks.put_nowait, chunk)
@@ -355,7 +366,7 @@ class TtsNode(_Speech):
reference = spoken.get(key)
if reference is not None and self._artifacts.has(reference["digest"]):
return dict(reference)
data = asyncio.run(client.speak(url + "/v1", sentence, self.cfg.voice))
data = self._call(client.speak(url + "/v1", sentence, self.cfg.voice)).result()
stored: dict[str, Any] = self._artifacts.put(
[data], name="speech.mp3", media_type="audio/mpeg"
)