- patch_audio_default_mp3.py: default /v1/audio/speech to response_format=mp3 when the caller omits it. LibreChat sends no response_format, and Tinfoil's voxtral-tts then serves WAV: measured ~8-17s warm (145-300KB) vs ~2.6-3.1s for mp3 (28-39KB, provider streams it). LibreChat labels the reply audio/mpeg regardless, so WAV bytes rode under an mp3 label. Explicit response_format from any caller still wins. - start.sh: scheduler tasks arrive as ARGUMENTS to this ENTRYPOINT script (docker run <image> <command>); they were booting a second tinfoil-proxy + LiteLLM and dying on the bind FATAL every run, so audio_keepalive never executed. Detect the arg and exec the task directly. - start.sh: own the warm path in the app container regardless of the scheduler container: ping tinfoil/voxtral-tts every 480s in the background (silent on success; failures append to /app/data/keepalive.log).
104 lines
4.1 KiB
Python
104 lines
4.1 KiB
Python
"""Default /v1/audio/speech to mp3 when the caller omits response_format.
|
|
|
|
Run at BUILD time (the runtime rootfs is read-only under Cloudron). Non-fatal:
|
|
if the target file or the anchor is missing — e.g. after a version bump — it
|
|
prints a warning and exits 0, so the build and the gateway still succeed. Look
|
|
for the ``[coop-patch]`` line in the build log.
|
|
|
|
Why: LibreChat's speech client sends no ``response_format`` on its TTS request
|
|
(TTSService.openAIProvider builds {input, model, voice} — the field is not in
|
|
its schema), and Tinfoil's voxtral-tts then serves WAV. Measured 2026-11-07
|
|
through the gateway: WAV ~8-17s warm per request (145-300 KB), while the SAME
|
|
model with ``response_format: "mp3"`` answers in ~2.6-3.1s (28-39 KB) — the
|
|
provider streams/encodes mp3 progressively. LibreChat additionally labels the
|
|
reply ``Content-Type: audio/mpeg`` unconditionally, so WAV bytes were served
|
|
under an mp3 label and browsers depended on MIME sniffing to play them.
|
|
|
|
Patch: default ``response_format`` to ``mp3`` (OpenAI's own documented default
|
|
for /v1/audio/speech) when the request omits it. An explicit response_format
|
|
from any caller still wins, so API members who want WAV can keep requesting
|
|
it. Scope: only the aspeech route; transcriptions are untouched.
|
|
|
|
Upstream: LiteLLM 1.103.2 forwards response_format verbatim and leaves the
|
|
provider default in place when it is absent.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import glob
|
|
import os
|
|
import sys
|
|
|
|
MARKER = "CO-OP PATCH (TTS default mp3, 2026-11-07)"
|
|
|
|
ANCHOR = ''' ### CALL HOOKS ### - modify incoming data / reject request before calling the model
|
|
data = await proxy_logging_obj.pre_call_hook(
|
|
user_api_key_dict=user_api_key_dict, data=data, call_type="aspeech"
|
|
)'''
|
|
|
|
INSERT = ANCHOR + '''
|
|
|
|
# CO-OP PATCH (TTS default mp3, 2026-11-07): LibreChat sends no
|
|
# response_format and Tinfoil's voxtral-tts then serves WAV — measured
|
|
# ~8-17s warm vs ~3s for mp3, which the provider streams. LibreChat
|
|
# labels the reply audio/mpeg regardless. Default to mp3 (OpenAI's
|
|
# documented default); an explicit response_format still wins.
|
|
if not data.get("response_format"):
|
|
data["response_format"] = "mp3"'''
|
|
|
|
|
|
def target_path() -> str:
|
|
if len(sys.argv) > 1:
|
|
return sys.argv[1]
|
|
env = os.environ.get("LITELLM_PROXY_SERVER")
|
|
if env:
|
|
return env
|
|
hits = []
|
|
try: # most reliable: ask the installed package where it lives
|
|
import litellm # noqa: PLC0415
|
|
_file = getattr(litellm, "__file__", None)
|
|
if _file:
|
|
hits.append(os.path.join(os.path.dirname(_file), "proxy", "proxy_server.py"))
|
|
except Exception:
|
|
pass
|
|
hits += glob.glob("/app/.venv/lib/python*/site-packages/litellm/proxy/proxy_server.py")
|
|
hits += glob.glob("/usr/local/lib/python3*/site-packages/litellm/proxy/proxy_server.py")
|
|
hits = [h for h in hits if os.path.exists(h)]
|
|
if not hits:
|
|
raise SystemExit("[coop-patch] could not locate litellm/proxy/proxy_server.py")
|
|
return sorted(hits)[0]
|
|
|
|
|
|
def main() -> int:
|
|
path = target_path()
|
|
try:
|
|
source = open(path).read()
|
|
except OSError as exc:
|
|
print(f"[coop-patch] cannot read {path}: {exc}")
|
|
return 0
|
|
|
|
if MARKER in source:
|
|
print(f"[coop-patch] {path} already patched, nothing to do")
|
|
return 0
|
|
|
|
count = source.count(ANCHOR)
|
|
if count != 1:
|
|
print(f"[coop-patch] WARNING aspeech pre_call_hook anchor found {count}x (need exactly 1) "
|
|
f"in {path}; TTS stays on the provider's default (WAV for Tinfoil)")
|
|
return 0
|
|
|
|
patched = source.replace(ANCHOR, INSERT, 1)
|
|
compile(patched, path, "exec") # refuse to write something that will not import
|
|
|
|
if not os.access(path, os.W_OK): # practice run against a read-only copy
|
|
print(f"[coop-patch] {path} is not writable; verified anchor and syntax only")
|
|
return 0
|
|
|
|
with open(path, "w") as handle:
|
|
handle.write(patched)
|
|
print(f"[coop-patch] applied TTS default mp3 to {path}")
|
|
return 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
sys.exit(main())
|