JS00000
|
34209021c8
|
fix: pytts second round not work
|
1 year ago |
lanvent
|
a0cbe9c3e2
|
feat(azure_voice.py): improve error logging in voiceToText method
|
1 year ago |
lanvent
|
a83e5a9b65
|
feat(azure_voice.py): improve error logging in textToVoice method
|
1 year ago |
JS00000
|
68361cddd2
|
wechatmp_service: image and voice reply supported
|
1 year ago |
lanvent
|
8f72e8c3e6
|
formatting code
|
1 year ago |
lanvent
|
acddadc406
|
feat: add convert pcm32 to pcm16
|
1 year ago |
lanvent
|
49ba278316
|
fix: use english filename
|
1 year ago |
lanvent
|
e71c600d10
|
feat: new itchat qrcode generator
|
1 year ago |
lanvent
|
dfb2e460b4
|
fix: voice length bug in wechaty
|
1 year ago |
lanvent
|
5badef8ba9
|
fix: correct sample rate when convert to silk
|
1 year ago |
lanvent
|
18aa5ce75c
|
fix: get correct audio format in pytts
|
1 year ago |
lanvent
|
1545a9f262
|
feat: support azure voice
|
1 year ago |
lanvent
|
02cd553990
|
refactor: using one processing logic in chat channel
|
1 year ago |
zhanws
|
06b02f5df8
|
解决百度语音合成的一些问题和参数化设置 (#676)
* 解决百度语音合成的一些问题和参数化设置
* 补充百度语音说明
|
1 year ago |
lanvent
|
e78886fb35
|
feat: new voice class pytts
|
1 year ago |
zwssunny
|
24de670c2c
|
解决语音的识别和转换兼容性
|
1 year ago |
zwssunny
|
61865bc408
|
修改google_voice为google合成,解决系统兼容性
|
1 year ago |
zwssunny
|
c2ea6214a9
|
增加百度语音识别
|
1 year ago |
zwssunny
|
b6684fe7a3
|
增加声音转换函数
|
1 year ago |
lanvent
|
ad6ae0b32a
|
refactor: use enum to specify type
|
1 year ago |
lanvent
|
8d2e81815c
|
compatible for voice
|
1 year ago |
wanggang
|
3db452ef71
|
[voice] using baidu service to gen reply voice
|
1 year ago |
wanggang
|
d7a8854fa1
|
[voice] add support for whisper-1 model
|
1 year ago |
wanggang
|
882e6c3576
|
[voice] add support for wispper
|
1 year ago |
wanggang
|
cc19017c01
|
[voice] add text to voice
|
1 year ago |
wanggang
|
1711a5c064
|
[voice] fix google voice exception issue
|
1 year ago |
wanggang
|
d38fc61043
|
[voice] add google voice support
|
1 year ago |