Commit Graph

840 Commits

Author SHA1 Message Date
Seefs
576775cbe1 Merge pull request #2098 from HynoR/chore/c1
chore: Update AWS claude 4.5 haiku model's information
2025-10-28 18:32:23 +09:00
Seefs
32beb5796c Merge pull request #2107 from wuhan005/wh/aws-client-support-proxy
feat: aws client supports proxy settings
2025-10-28 18:31:56 +09:00
CaIon
a00c6393c5 feat: implement audio duration retrieval without ffmpeg dependencies 2025-10-28 15:50:45 +08:00
iwu
ea6dc0c338 feat: aws client supports proxy settings
Signed-off-by: iwu <iwu@tencent.com>
2025-10-27 15:00:20 +08:00
HynoR
87d72a50c9 chore: update aws claude 4.5 haiku model's information 2025-10-24 14:21:17 +08:00
feitianbubu
fe9b092b0b feat: doubao-seedream support image edit 2025-10-23 21:19:33 +08:00
IcedTangerine
01b3c35b70 Merge pull request #2087 from feitianbubu/pr/doubao-tts-stream
feat: doubao tts support streaming realtime audio
2025-10-22 17:44:01 +08:00
feitianbubu
fd6cd838f7 refactor: clean up doubao tts code 2025-10-22 17:06:13 +08:00
feitianbubu
828bb17d2c feat: doubao tts add is stream check 2025-10-22 13:39:16 +08:00
feitianbubu
23c22708f2 feat: doubao tts support streaming realtime audio 2025-10-22 13:39:16 +08:00
feitianbubu
f617ff8741 feat: openai tts support streaming realtime audio 2025-10-22 13:33:01 +08:00
Seefs
bba0cbe6f1 Merge pull request #2070 from QuantumNous/ali-channel-support-stream-options
Ali channel support stream options
2025-10-20 23:24:33 +08:00
IcedTangerine
c74d89c47a chore: Comment out debug log in adaptor.go
Comment out the debug log for MiniMax TTS Request.
2025-10-20 17:48:08 +08:00
feitianbubu
d52505cac1 feat: opt minimax tts req struct 2025-10-20 16:26:50 +08:00
feitianbubu
a2d34b9e47 feat: add minimax api adaptor 2025-10-20 16:26:50 +08:00
feitianbubu
0a8e54de20 feat: add minimax tts 2025-10-20 16:26:50 +08:00
creamlike1024
2a2dd438db refactor: remove unused functions and imports from ali text handler 2025-10-18 17:00:28 +08:00
IcedTangerine
8ac801261d Merge pull request #2068 from feitianbubu/pr/doubao-speech-emotion
豆包语音2.0音色支持情感,情绪,音量
2025-10-18 14:30:17 +08:00
Seefs
0d62db7ce7 Merge pull request #2065 from somnifex/main
fix: handle JSON parsing for thinking content in ollama stream
2025-10-18 13:02:56 +08:00
feitianbubu
13362887dd fix: doubao audio speedRadio to speed 2025-10-18 01:48:36 +08:00
feitianbubu
412b935a4d feat: AudioRequest add metadata support custom params 2025-10-18 01:48:36 +08:00
IcedTangerine
319680d052 Fix error message for invalid API key format 2025-10-18 00:13:28 +08:00
feitianbubu
0952631fa2 feat: add doubao tts usage token 2025-10-17 22:06:45 +08:00
feitianbubu
1be4e12ca0 feat: switch to official TTS only when baseUrl is Volcano's official URL 2025-10-17 22:06:45 +08:00
feitianbubu
f052f8ba22 feat: add doubao audio tts 2025-10-17 22:06:45 +08:00
somnifex
e4a2904c56 fix: handle JSON parsing for thinking content in ollama stream and chat handlers 2025-10-17 18:35:08 +08:00
CaIon
6df44134ab refactor: rename AWS model ID and region prefix functions for clarity 2025-10-16 12:10:55 +08:00
CaIon
48cadc95f3 feat: 修复aws渠道-thinking后缀不生效的问题 2025-10-15 18:49:27 +08:00
CaIon
1fdb54651b feat: 临时兼容aws使用链接媒体 2025-10-15 18:21:19 +08:00
CaIon
59caea8f34 feat: support aws bedrock api-keys-use 2025-10-15 17:29:10 +08:00
CaIon
31e09b960f refactor: aws 2025-10-15 16:44:33 +08:00
CaIon
5069482d22 refactor: update ConvertToOpenAIVideo method to return byte array and improve error handling 2025-10-14 23:03:17 +08:00
Seefs
c62daee6f3 Merge pull request #2036 from etnAtker/siliconflow-images-generations
feat: 添加SiliconFlow图像生成接口自动转换支持
2025-10-14 13:05:04 +08:00
CaIon
7391b15b4b fix: remove redundant error handling for empty Gemini API response 2025-10-13 21:58:50 +08:00
etnAtker
fc2486d878 fix: 修复PR的潜在问题
1. 解析ImageRequest的Extra时,处理err
2. DoResponse方法添加RelayModeImagesGenerations(fallthrough)
2025-10-13 20:20:08 +08:00
etnAtker
933e42e5df feat: 添加SiliconFlow图像生成接口自动转换支持
1. 将对SiliconFlow渠道的RelayModeImagesGenerations请求,转发至v1/images/generations端点。
2. SiliconFlow图像生成接口额外参数适配。
2025-10-13 20:06:33 +08:00
yanggh
b6f352735e fix(convert): 修复 OpenAI 转 Claude 流时 thinking 块的格式问题
将 `ClaudeMediaMessage.Thinking` 的类型从 `string` 修改为 `*string`,以解决 `omitempty` 导致 `"thinking": ""` 字段在 JSON 序列化时被忽略的问题。

同时更新了 `service/convert.go` 和 `relay/channel/claude/relay-claude.go` 中的相关逻辑,以兼容新的指针类型,确保生成的 Claude 事件流符合官方规范。
2025-10-13 19:32:17 +08:00
skynono
7c543a9e19 feat: jimeng images base64 limit (#2032) 2025-10-13 15:17:23 +08:00
Seefs
0dfd8f2743 Merge pull request #2029 from feitianbubu/pr/jimeng-support-oai-files
feat: jimeng use openai sdk input_reference i2v
2025-10-13 14:14:43 +08:00
feitianbubu
61f388bf84 feat: jimeng use openai sdk input_reference i2v 2025-10-13 13:06:03 +08:00
Xyfacai
b7a07e1ef7 refactor: Openai video model 移动到 dto 2025-10-13 11:45:45 +08:00
CaIon
063926dd29 fix: update error messages for unsupported parameter names in Google extra body 2025-10-12 22:21:45 +08:00
feitianbubu
7f9309ee17 feat: add vidu use openai sdk 2025-10-11 17:11:44 +08:00
feitianbubu
d733803c8a fix: kling create video via openai sdk 2025-10-11 17:11:44 +08:00
feitianbubu
d724f25db4 refactor: add openaiVideo and method 2025-10-11 17:05:36 +08:00
feitianbubu
7c7313a937 feat: add jimeng use openai sdk 2025-10-11 17:05:33 +08:00
Seefs
5010f2d004 format: package name -> github.com/QuantumNous/new-api (#2017) 2025-10-11 15:30:09 +08:00
feitianbubu
c0859c056f feat: add openai sdk for kling 2025-10-11 02:43:56 +08:00
feitianbubu
69f497e350 refactor: openAI video use OpenAIVideoConverter 2025-10-11 02:43:43 +08:00
Calcium-Ion
2b39ae557c Merge pull request #1998 from seefs001/feature/pplx-channel
feat: pplx channel
2025-10-10 16:33:27 +08:00