Commit Graph

28 Commits

Author SHA1 Message Date
Harry
951460b9f1
Merge pull request #715 from michaeltmk/feat/custom_audio
feat: add custom audio file support
2025-12-14 12:02:56 +08:00
zhangxindong
d65e126486 feat: integrate Google Gemini TTS with 15 voice options
- Add gemini_tts() function with proper PCM audio handling
- Support 15 Gemini voices (Zephyr, Puck, Kore, etc.)
- Fix audio data format issue preventing video generation
- Add Gemini TTS option to WebUI settings
- Update .gitignore to exclude debug files
2025-07-08 10:39:22 +08:00
michael tse
f6c40deec6 feat: add custom audio file support 2025-05-25 17:04:56 +08:00
harry
4d5ca7f6f4 perf: validate Azure speech key and region before creating speech 2025-05-10 17:20:44 +08:00
yyhhyyyyyy
45f32756a3 feat: increase siliconflow TTS services 2025-05-09 23:31:04 +08:00
yyhhyyyyyy
22f47d90de feat: add TTS services provider selection list 2025-05-09 22:14:43 +08:00
harry
35a7ef657a feat: remove voice filter 2025-05-08 18:09:26 +08:00
evan.zhang5
ab1bd03f0b refactor: Refactor the get_all_azure_voices function to reduce the amount of code by half 2025-02-27 17:31:32 +08:00
yyhhyyyyyy
afd064e15d 🎨 style: Format Code 2024-12-10 10:34:56 +08:00
yyhhyyyyyy
6288b70ae2 ⬆️ deps: Upgrade dependencies to latest versions and address minor issues 2024-12-05 10:16:38 +08:00
yyhhyyyyyy
905841965a Format project code 2024-07-24 14:59:06 +08:00
yyhhyyyyyy
63fb848a17 1. Add azure_tts_v1 to control the speed of speech 2024-07-19 11:06:34 +08:00
harry
6de3d6eedc 1. support voice preview
2, update version to 1.1.6
2024-05-13 18:29:59 +08:00
harry
c7c7b4847e optimize code 2024-04-22 16:25:13 +08:00
vuisme
1c35e50563 Add vietnamese and sample font Vietnamese. String pre-translated by chatGPT 2024-04-17 10:57:16 +07:00
harry
176660b442 support azure new speech voice 2024-04-15 17:45:05 +08:00
harry
a17d52c1ae optimize segmentation 2024-04-13 21:50:45 +08:00
wangxingda
2df2cc0dab add default subtitle encoding to utf-8 2024-04-05 19:37:53 +08:00
harry
c5e396d484 Optimize subtitle generation in edge mode (#133) 2024-04-04 09:47:29 +08:00
harry
52bf4d5f4f Optimized subtitle generation in edge mode 2024-03-30 17:33:54 +08:00
harry
bc8e005f59 1. Added multi-language support to the UI
2. Optimized the voice name
3. Other UI optimizations
2024-03-29 17:13:25 +08:00
harry
c5dad43c2c 1, Add language settings for llm outputs
2, Optimize llm prompts
3, Add timeout handling for material downloads
2024-03-26 16:48:14 +08:00
harry
b471a272b6 1, optimize the subtitle generation in edge mode
2, optimize the llm prompt, use the same language as the video subject
2024-03-24 17:52:12 +08:00
harry
0771b3268c 1, 增加一次性输出多个视频
2, 增加背景音乐音量设置
3, 增加字幕位置
4, UI优化
5, 一些其他Bug修复和优化
2024-03-23 15:31:34 +08:00
harry
ce4b3771b6 1, 支持AI生成文案预览
2, 支持自定义视频文案,关键词
3, 可选择是否启用字幕
4, UI优化
5, 一些其他bug修复和优化
2024-03-22 17:46:56 +08:00
harry
6bfb04f755 changed to sync 2024-03-18 21:39:47 +08:00
harry
b5ba1e6b09 fixed: asyncio.run() cannot be called from a running event loop 2024-03-16 08:55:15 +08:00
harry
06df797234 init 2024-03-11 16:37:49 +08:00