mirror of
https://github.com/zhayujie/chatgpt-on-wechat.git
synced 2026-06-02 00:57:41 +08:00
b80c3fe5a8
- rewrite streaming reply to official cardkit v2.0 API (default on, auto-fallback) - fix Whisper hallucination: bump ASR sample rate to 16k, pass language=zh - fix lock-over-IO and tmp file cleanup from #2791 - drop deprecated feishu_bot_name; quiet unknown-key warnings - docs: cardkit permission and feishu_stream_reply usage
79 lines
3.2 KiB
Python
79 lines
3.2 KiB
Python
"""
|
|
google voice service
|
|
"""
|
|
import json
|
|
|
|
from bridge.reply import Reply, ReplyType
|
|
from common.log import logger
|
|
from config import conf
|
|
from voice.voice import Voice
|
|
import requests
|
|
from common import const
|
|
import datetime, random
|
|
|
|
class OpenaiVoice(Voice):
|
|
def __init__(self):
|
|
# No-op: this implementation calls OpenAI HTTP endpoints directly via
|
|
# `requests`, so it does not need a global SDK to be configured.
|
|
pass
|
|
|
|
def voiceToText(self, voice_file):
|
|
logger.debug("[Openai] voice file name={}".format(voice_file))
|
|
try:
|
|
file = open(voice_file, "rb")
|
|
api_base = conf().get("open_ai_api_base") or "https://api.openai.com/v1"
|
|
url = f'{api_base}/audio/transcriptions'
|
|
headers = {
|
|
'Authorization': 'Bearer ' + conf().get("open_ai_api_key"),
|
|
# 'Content-Type': 'multipart/form-data' # 加了会报错，不知道什么原因
|
|
}
|
|
files = {
|
|
"file": file,
|
|
}
|
|
data = {
|
|
"model": "whisper-1",
|
|
}
|
|
response = requests.post(url, headers=headers, files=files, data=data)
|
|
response_data = response.json()
|
|
if response.status_code != 200 or "text" not in response_data:
|
|
logger.error(
|
|
f"[Openai] voiceToText failed: status={response.status_code}, "
|
|
f"resp={response_data}"
|
|
)
|
|
reply = Reply(ReplyType.ERROR, "我暂时还无法听清您的语音，请稍后再试吧~")
|
|
else:
|
|
text = response_data["text"]
|
|
reply = Reply(ReplyType.TEXT, text)
|
|
logger.info("[Openai] voiceToText text={} voice file name={}".format(text, voice_file))
|
|
except Exception as e:
|
|
logger.error(f"[Openai] voiceToText exception: {e}", exc_info=True)
|
|
reply = Reply(ReplyType.ERROR, "我暂时还无法听清您的语音，请稍后再试吧~")
|
|
finally:
|
|
return reply
|
|
|
|
|
|
def textToVoice(self, text):
|
|
try:
|
|
api_base = conf().get("open_ai_api_base") or "https://api.openai.com/v1"
|
|
url = f'{api_base}/audio/speech'
|
|
headers = {
|
|
'Authorization': 'Bearer ' + conf().get("open_ai_api_key"),
|
|
'Content-Type': 'application/json'
|
|
}
|
|
data = {
|
|
'model': conf().get("text_to_voice_model") or const.TTS_1,
|
|
'input': text,
|
|
'voice': conf().get("tts_voice_id") or "alloy"
|
|
}
|
|
response = requests.post(url, headers=headers, json=data)
|
|
file_name = "tmp/" + datetime.datetime.now().strftime('%Y%m%d%H%M%S') + str(random.randint(0, 1000)) + ".mp3"
|
|
logger.debug(f"[OPENAI] text_to_Voice file_name={file_name}, input={text}")
|
|
with open(file_name, 'wb') as f:
|
|
f.write(response.content)
|
|
logger.info(f"[OPENAI] text_to_Voice success")
|
|
reply = Reply(ReplyType.VOICE, file_name)
|
|
except Exception as e:
|
|
logger.error(e)
|
|
reply = Reply(ReplyType.ERROR, "遇到了一点小问题，请稍后再问我吧")
|
|
return reply
|