62 lines
1.6 KiB
Plaintext
62 lines
1.6 KiB
Plaintext
# OpenAI-compatible Audio Transcription API (ASR)
|
|
# POST /v1/audio/transcriptions
|
|
# Required params: model, catelogid, audio_file (audio URL or base64)
|
|
# Optional params: language
|
|
#
|
|
# Example request:
|
|
# {
|
|
# "model": "qwen3-asr-flash",
|
|
# "catelogid": "asr",
|
|
# "audio_file": "https://example.com/audio.wav"
|
|
# }
|
|
#
|
|
# Response:
|
|
# {
|
|
# "text": "识别出的文本内容",
|
|
# "usage": { "duration_seconds": 5.2 }
|
|
# }
|
|
|
|
userid = await get_user()
|
|
userorgid = await get_userorgid()
|
|
if userid is None:
|
|
debug('need login')
|
|
return openai_403()
|
|
|
|
# Validate required parameters
|
|
if not params_kw.model:
|
|
d = return_error('Missing required parameter: model')
|
|
return json_response(d, status=400)
|
|
|
|
if not params_kw.catelogid:
|
|
d = return_error('Missing required parameter: catelogid')
|
|
return json_response(d, status=400)
|
|
|
|
if not params_kw.audio_file:
|
|
d = return_error('Missing required parameter: audio_file')
|
|
return json_response(d, status=400)
|
|
|
|
lctype = params_kw.catelogid
|
|
|
|
env = request._run_ns
|
|
llmid = await env.get_llmid_cached(env, params_kw.model, lctype)
|
|
if not llmid:
|
|
debug(f'{params_kw.model=} not found for catalog {lctype}')
|
|
return openai_400()
|
|
params_kw.llmid = llmid
|
|
params_kw.llmcatelogid = lctype
|
|
|
|
debug(f'{params_kw.llmid=}')
|
|
|
|
# Check balance
|
|
f = await checkCustomerBalance(params_kw.llmid, userid, userorgid)
|
|
if not f:
|
|
debug(f'{userid=} balance not enough')
|
|
return openai_429()
|
|
|
|
# Generate task ID and attach to params
|
|
if not params_kw.transno:
|
|
params_kw.transno = getID()
|
|
|
|
# Call inference (ASR is synchronous)
|
|
return await inference(request, env=env)
|