zhayujie
|
5ad53c2b9c
|
fix: reduce error noise when converting speech to text
|
il y a 1 an |
zhayujie
|
7218463f9e
|
docs: update README
|
il y a 1 an |
zhayujie
|
0c8f292e12
|
feat: add tts speech model
|
il y a 1 an |
zhayujie
|
f001ac6903
|
feat: add dalle3 gpt-4-turbo model change
|
il y a 1 an |
uezhenxiang2023
|
db4998a56b
|
replace requests with elevenlabs for audio generation
|
il y a 1 an |
uezhenxiang2023
|
acbd506568
|
add ElevenLabs TTS to voice factory
|
il y a 1 an |
lanvent
|
c34d70b3cb
|
fix: add warning log when pysilk module is not installed
|
il y a 1 an |
chenzefeng.09
|
e539ae3b69
|
fix: baidu voice init params type error
|
il y a 1 an |
SSMario
|
4dbc54fa15
|
Revert "feat: 增加eleventLabs"
This reverts commit 1d4ff796d7 .
|
il y a 1 an |
SSMario
|
1d4ff796d7
|
feat: 增加eleventLabs
|
il y a 1 an |
lanvent
|
fb22e01b89
|
fix: send voice in wechatcomapp rightly
|
il y a 1 an |
lanvent
|
76a81d5360
|
feat(wechatcomapp): add support for splitting long audio files
|
il y a 1 an |
lanvent
|
9fea949b25
|
fix(azure_voice.py): log error details instead of cancellation details
|
il y a 1 an |
JS00000
|
dca5c058e0
|
fix: Avoid the same filename under multithreading (#933)
|
il y a 1 an |
lanvent
|
1e09bd0e76
|
feat(azure_voice): add language detection, support mulitple languages
|
il y a 1 an |
lanvent
|
cae12eb187
|
feat: add baidu translate api
|
il y a 1 an |
lanvent
|
618c94edb8
|
formatting: run precommit on all files
|
il y a 1 an |
JS00000
|
1cd6a71ce0
|
fix the bug of pytts in linux
|
il y a 1 an |
lanvent
|
89dd8a1db6
|
refactor(wechatmp): use wechatpy to handle wechatmp messages
feat(wechatmp): add support for image and voice replies
|
il y a 1 an |
lanvent
|
c60f0517fb
|
refactor(audio_convert.py): remove redundant functions
|
il y a 1 an |
JS00000
|
34209021c8
|
fix: pytts second round not work
|
il y a 1 an |
lanvent
|
ab83dacb76
|
feat(wechatcom): add support for sending voice messages
|
il y a 1 an |
lanvent
|
a0cbe9c3e2
|
feat(azure_voice.py): improve error logging in voiceToText method
|
il y a 1 an |
lanvent
|
a83e5a9b65
|
feat(azure_voice.py): improve error logging in textToVoice method
|
il y a 1 an |
JS00000
|
68361cddd2
|
wechatmp_service: image and voice reply supported
|
il y a 1 an |
lanvent
|
8f72e8c3e6
|
formatting code
|
il y a 1 an |
lanvent
|
acddadc406
|
feat: add convert pcm32 to pcm16
|
il y a 1 an |
lanvent
|
49ba278316
|
fix: use english filename
|
il y a 1 an |
lanvent
|
e71c600d10
|
feat: new itchat qrcode generator
|
il y a 1 an |
lanvent
|
dfb2e460b4
|
fix: voice length bug in wechaty
|
il y a 1 an |
lanvent
|
5badef8ba9
|
fix: correct sample rate when convert to silk
|
il y a 1 an |
lanvent
|
18aa5ce75c
|
fix: get correct audio format in pytts
|
il y a 1 an |
lanvent
|
1545a9f262
|
feat: support azure voice
|
il y a 1 an |
lanvent
|
02cd553990
|
refactor: using one processing logic in chat channel
|
il y a 1 an |
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
|
il y a 1 an |
lanvent
|
e78886fb35
|
feat: new voice class pytts
|
il y a 1 an |
zwssunny
|
24de670c2c
|
解决语音的识别和转换兼容性
|
il y a 1 an |
zwssunny
|
61865bc408
|
修改google_voice为google合成,解决系统兼容性
|
il y a 1 an |
zwssunny
|
c2ea6214a9
|
增加百度语音识别
|
il y a 1 an |
zwssunny
|
b6684fe7a3
|
增加声音转换函数
|
il y a 1 an |
lanvent
|
ad6ae0b32a
|
refactor: use enum to specify type
|
il y a 1 an |
lanvent
|
8d2e81815c
|
compatible for voice
|
il y a 1 an |
wanggang
|
3db452ef71
|
[voice] using baidu service to gen reply voice
|
il y a 1 an |
wanggang
|
d7a8854fa1
|
[voice] add support for whisper-1 model
|
il y a 1 an |
wanggang
|
882e6c3576
|
[voice] add support for wispper
|
il y a 1 an |
wanggang
|
cc19017c01
|
[voice] add text to voice
|
il y a 1 an |
wanggang
|
1711a5c064
|
[voice] fix google voice exception issue
|
il y a 1 an |
wanggang
|
d38fc61043
|
[voice] add google voice support
|
il y a 1 an |