65 lines
1.7 KiB
Plaintext
65 lines
1.7 KiB
Plaintext
# OpenAI-compatible Text-to-Speech API
|
|
# POST /v1/audio/speech
|
|
# Required params: model, catelogid, prompt (text to synthesize)
|
|
# Optional params: speaker (voice_id), speed, emotion
|
|
#
|
|
# Example request:
|
|
# {
|
|
# "model": "speech-2.6-turbo",
|
|
# "catelogid": "tts",
|
|
# "prompt": "你好，欢迎使用语音合成服务",
|
|
# "speaker": "female-tianmei",
|
|
# "speed": 1.0,
|
|
# "emotion": "happy"
|
|
# }
|
|
#
|
|
# Response (stream, hex audio chunks):
|
|
# {
|
|
# "status": "SUCCEEDED",
|
|
# "audio": "base64_encoded_audio_data"
|
|
# }
|
|
|
|
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.prompt:
|
|
d = return_error('Missing required parameter: prompt (text to synthesize)')
|
|
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 (TTS can be stream or sync depending on model)
|
|
return await inference(request, env=env)
|