zhayujie
bccce2d7cb
feat(models): support xiaomi mimo
2026-05-28 10:49:52 +08:00
zhayujie
116fb27257
fix: robust tool args JSON parsing for non-strict providers #2823
2026-05-27 18:37:54 +08:00
zhayujie
b8333e351c
feat(voice): rework TTS/ASR stack and unify tool/skill config schema
2026-05-21 16:00:54 +08:00
zhayujie
2b90f377e6
feat(voice): add dashscope & zhipu ASR, in-page mic input
2026-05-20 22:36:37 +08:00
zhayujie
b80c3fe5a8
feat(feishu): enhance #2791 with cardkit streaming + ASR fixes
...
- 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
2026-05-05 14:15:25 +08:00
ooaaooaa123
4d1f059c0d
feat(feishu): add voice message support and streaming text reply
...
- Receive audio messages: map msg_type=audio to ContextType.VOICE and
download opus file via lazy _prepare_fn for STT pipeline
- Send voice replies: upload opus audio via Feishu file API, auto-convert
non-opus formats (e.g. mp3) using pydub before upload
- Streaming text reply: inject on_event callback into context; send a
card
placeholder on first delta, then PATCH-update it in-place at a
configurable interval (feishu_stream_interval_ms) to achieve typewriter
effect; set feishu_streamed=True to suppress duplicate send()
- Enable NOT_SUPPORT_REPLYTYPE=[] to unblock voice and image reply types
- Fix AudioSegment mutation bug in audio_convert.py: set_frame_rate /
set_channels return new objects and must be reassigned
- Add -nostdin to ffmpeg invocation to prevent stdin deadlock in daemon
- Add feishu_bot_name, feishu_stream_reply, feishu_stream_interval_ms
config keys to config-template.json
2026-04-30 16:14:57 +08:00
zhayujie
8752f0cc60
refactor(openai): drop SDK dependency and switch to native HTTP client
2026-04-27 20:21:54 +08:00
octo-patch
c34308cbd4
feat: add MiniMax-M2.7-highspeed model and MiniMax TTS support
...
- Add MiniMax-M2.7-highspeed constant to const.py and MODEL_LIST
- Update MinimaxBot default model from MiniMax-M2.1 to MiniMax-M2.7
- Add MinimaxVoice TTS provider (voice/minimax/minimax_voice.py)
- Supports speech-2.8-hd and speech-2.8-turbo models
- SSE streaming with hex-decoded audio chunks
- Reuses MINIMAX_API_KEY
- Register MinimaxVoice in voice factory
- Add unit tests (14 tests, all passing)
- Update README with MiniMax-M2.7-highspeed and TTS configuration
2026-04-11 17:03:44 +08:00
zhayujie
c4b5f7fbae
refactor: remove unavailable channels
2026-03-16 11:05:45 +08:00
saboteur7
501866d12a
feat: optimize document and model usage
2026-02-03 02:58:15 +08:00
vision
e0dd21406d
Update baidu_voice.py
2025-05-23 15:13:28 +08:00
thzjy
814ce7a43b
fix: 修复百度语音合成长文处理
2025-05-18 17:32:17 +08:00
gaojia
ead5f9926b
删除funasr
2025-03-27 10:13:38 +08:00
gaojia
814b6753c2
删除配置文件中的注释
2025-03-26 17:33:39 +08:00
gaojia
ce505251f8
修改配置文件及文件夹名称
2025-03-26 10:01:41 +08:00
gaojia
ec1c6c7b92
新增腾讯语音
2025-03-04 09:56:26 +08:00
Zheng
3effd5afd1
fix azure voice error
2024-07-30 17:10:02 +08:00
kody
f0e416455f
增加了使用阿里云进行语音识别的引擎
2024-07-15 22:03:31 +08:00
Saboteur7
b8c5174da5
docs: xunfei voice comment
2024-06-04 13:49:44 +08:00
Saboteur7
1f6f9103d9
docs: update README.md
2024-06-04 12:50:59 +08:00
Saboteur7
8b2d1189db
Merge pull request #1999 from njnuko/voice-xunfei
...
add xunfei voice
2024-06-04 11:43:55 +08:00
Saboteur7
b777f27cb7
chore: remove some xunfei voice log
2024-06-04 11:42:05 +08:00
6vision
be13cc3194
Changed sampling rate
2024-05-23 01:34:20 +08:00
njnuko
6fed719e09
add Xunfei Voice
...
Signed-off-by: njnuko <njnuko@163.com >
2024-05-20 15:04:23 +08:00
zhayujie
4db19f816f
feat: update service url
2024-05-03 14:10:07 +08:00
Lecter
b494ee2f1c
fix openai voice_to_text whisper
2024-04-14 14:33:17 +08:00
zhayujie
c662fa4c63
Merge pull request #1871 from cgnannan/master
...
修复 Issues #1868提到的elevenlabs sdk更新问题
2024-04-09 15:52:35 +08:00
zhayujie
db2ee802ca
chore: log optimization
2024-04-09 15:35:18 +08:00
cgnannan
6ddddffc0f
update SDK version of elevenlabs and corresponding code snippets.
2024-04-01 06:26:39 +00:00
zhayujie
f71820bf4e
Merge pull request #1787 from uxfion/edge-tts
...
feat: edge-tts
2024-03-25 15:24:14 +08:00
Lecter
3a20461abf
add edge-tts
2024-03-04 00:14:19 +08:00
FMStereo
977d3bc02e
百度语音转写支持8000采样率, pcm_s16le编码, 单通道语音的组合
2024-01-18 12:46:18 +08:00
zhayujie
ae4077ed6c
fix: config adjust
2023-12-08 14:29:14 +08:00
zhayujie
8c2a53a504
Merge pull request #1573 from chazzjimel/master
...
add ali voice output
2023-12-08 13:34:54 +08:00
zhayujie
9d4afeac31
feat: speech support app_code bind
2023-12-07 22:44:43 +08:00
跃迁
6b30dced43
Merge branch 'zhayujie:master' into master
2023-12-06 00:44:18 +08:00
chazzjimel
293a03b7c8
add ali voice output
...
增加阿里云语音输出接口
2023-12-06 00:43:19 +08:00
zhayujie
e5ba26febe
fix: tts voice base url
2023-12-06 00:31:31 +08:00
chazzjimel
d89b056886
add ali voice output
...
增加阿里云语音输出支持。
2023-12-03 18:19:03 +08:00
zhayujie
5ad53c2b9c
fix: reduce error noise when converting speech to text
2023-11-16 10:54:24 +08:00
zhayujie
7218463f9e
docs: update README
2023-11-10 16:06:58 +08:00
zhayujie
0c8f292e12
feat: add tts speech model
2023-11-10 10:48:52 +08:00
zhayujie
f001ac6903
feat: add dalle3 gpt-4-turbo model change
2023-11-10 10:11:02 +08:00
uezhenxiang2023
db4998a56b
replace requests with elevenlabs for audio generation
2023-08-20 10:58:26 +08:00
uezhenxiang2023
acbd506568
add ElevenLabs TTS to voice factory
2023-08-19 11:20:47 +08:00
lanvent
c34d70b3cb
fix: add warning log when pysilk module is not installed
2023-06-10 11:22:12 +08:00
chenzefeng.09
e539ae3b69
fix： baidu voice init params type error
2023-06-09 18:54:58 +08:00
lanvent
fb22e01b89
fix: send voice in wechatcomapp rightly
2023-04-27 23:04:24 +08:00
lanvent
76a81d5360
feat(wechatcomapp): add support for splitting long audio files
2023-04-27 22:47:50 +08:00
lanvent
9fea949b25
fix(azure_voice.py): log error details instead of cancellation details
2023-04-27 11:42:19 +08:00
