Xin Wang
92d20e59e9
feat: Add SiliconFlow TTS API support with custom base URL and model selection
...
This commit adds comprehensive support for using SiliconFlow's TTS API as an alternative to OpenAI, including:
Features:
- Configurable API base URL (Settings > API Base URL)
- TTS model selection dropdown (CosyVoice2-0.5B, OpenAI compatible models)
- Dynamic voice options based on selected model
- Editable voice dropdown (Combobox) supporting custom voice IDs
- Automatic voice formatting for SiliconFlow (model:voice format)
- Debug logging for troubleshooting API calls
- Warning for incorrect base URL format
Changes:
- utils/settings_manager.py: Added api_base_url and tts_model settings
- utils/text_to_mic.py:
- Added get_available_tts_models() for model options
- Added get_siliconflow_voices() for SiliconFlow voices
- Added change_api_base_url() method with validation
- Added TTS model dropdown in GUI
- Converted voice dropdown to Combobox for typing support
- Added on_voice_exit() for validation
- Updated API call to use selected model and formatted voice
- text-to-mic-cli.py: Added OPENAI_API_BASE_URL and OPENAI_TTS_MODEL env var support
- Readme.md: Updated documentation with SiliconFlow usage instructions
Supported Models:
- FunAudioLLM/CosyVoice2-0.5B (SiliconFlow - multi-language, emotional)
- tts-1, tts-1-hd (OpenAI compatible)
- gpt-4o-mini-tts (OpenAI default)
SiliconFlow Voices (CosyVoice2-0.5B):
- Male: alex, benjamin, charles, david
- Female: anna, bella, claire, diana
- Custom voices via voice ID entry
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com >
2026-01-27 17:12:34 +08:00
Andrew Ward
20358adafb
update gitignore
2025-03-25 10:43:06 +00:00
Andrew Ward
13de96fdad
update version number
2025-03-25 10:09:13 +00:00
Andrew Ward
a529835037
address bugs around api key and non api key app modes, also refresh app on key input. Grey out buttons and add warnings for disabled features
2025-03-25 10:06:39 +00:00
Andrew Ward
aa092a3c15
update to add system voices and enable basic app use without an API key
2025-03-25 09:44:32 +00:00
Andrew Ward
2ed693edd8
readme new line
2025-03-22 12:53:58 +00:00
Andrew Ward
dac0e8ce0e
add screenshots and update readme
2025-03-22 12:53:22 +00:00
Andrew Ward
86de047170
version 1.4.0
2025-03-22 12:43:31 +00:00
Andrew Ward
e69e45343e
fix main ui select box layout and area sizing
2025-03-22 12:30:06 +00:00
Andrew Ward
a2a7c6f9a5
lots of ux improvements and small bug fixes
2025-03-22 12:18:40 +00:00
Andrew Ward
0e3cb8925a
add check for updates banner
2025-03-22 11:47:57 +00:00
Andrew Ward
7633788da6
version checking nearly working
2025-03-22 11:27:22 +00:00
Andrew Ward
6054bd378f
further code tidyup
2025-03-22 11:06:07 +00:00
Andrew Ward
900e2b9ef7
refactor settings handling to its own class
2025-03-22 11:01:33 +00:00
Andrew Ward
0f53b782b0
refactor code to move ai editing settings to its own file
2025-03-22 10:57:13 +00:00
Andrew Ward
039b9ee90d
improvements to AI copyediting ux
2025-03-22 10:50:16 +00:00
Andrew Ward
41d69f9f95
make the app remember the last selected input and playback devices
2025-03-22 10:23:52 +00:00
Andrew Ward
8d0431ca20
make setting loading more robust so the app wont crash if new ones are added between releases
2025-03-22 10:22:29 +00:00
Andrew Ward
ed9e89f6c9
fix licence file loading
2025-03-22 10:19:16 +00:00
Andrew Ward
469826056c
update icon, app head text, and versioning
2025-03-22 10:17:31 +00:00
Andrew Ward
bc130badc6
tidy up the design of the tone preset manager
2025-03-22 10:05:21 +00:00
Andrew Ward
4bc5a38854
update readme screenshot
2025-03-21 19:46:23 +00:00
Andrew Ward
758a804612
update version
2025-03-21 19:36:33 +00:00
Andrew Ward
62e6db331b
add ability to easily stop a record and play process mid way through
2025-03-21 19:30:08 +00:00
Andrew Ward
e6b8973685
add cancel operation keyboard shortcut
2025-03-21 19:19:31 +00:00
Andrew Ward
450a58a7d8
implement banner showing and hiding
2025-03-21 19:12:17 +00:00
Andrew Ward
e2bf3f3f91
update presets area to scale to fit scaled window sizes
2025-03-21 18:29:43 +00:00
Andrew Ward
170199c604
update presets performance and refactor class, plus change more icons
2025-03-21 18:18:34 +00:00
Andrew Ward
704b6269bc
add additional voices and deep preset
2025-03-21 17:54:11 +00:00
Andrew Ward
950a9b71cf
further improve ui and cta
2025-03-21 13:20:32 +00:00
Andrew Ward
86433d787a
update presets
2025-03-21 12:54:43 +00:00
Andrew Ward
8a5f92b3cd
add new interface for setting keyboard shortcuts
2025-03-21 12:49:05 +00:00
Andrew Ward
ece9d883cf
hotkey manager working
2025-03-21 12:37:14 +00:00
Andrew Ward
1f476f2c60
update transcription model from whisper to gpt-4o-transcribe
2025-03-21 11:16:24 +00:00
Andrew Ward
651a09d496
improve style of the tone manager
2025-03-21 11:13:16 +00:00
Andrew Ward
b42b267141
update to enable tone of voice playback
2025-03-21 11:09:42 +00:00
Andrew Ward
c353e79b6a
update button style
2025-03-21 10:31:25 +00:00
Andrew Ward
d95382e4b3
update ui
2025-03-21 10:21:06 +00:00
Andrew Ward
d365fc43e6
remove clam yellowy bg colour
2025-03-21 10:14:23 +00:00
Andrew Ward
794c71088a
refactor code into smaller subclasses
2025-02-25 14:25:33 +00:00
Andrew Ward
1aa99026b0
remove wav restriction
2024-11-12 11:17:42 +00:00
Andrew Ward
5550d6c3fe
update readme
2024-10-29 11:15:08 +00:00
Andrew Ward
f5a9363ff7
move presets example json to assets to prevent comiled code running issues
2024-10-29 11:09:54 +00:00
Andrew Ward
f4ae2a9e39
fix some ui issues, add scrolling to presets area, update readme instructions, other small QOL improvements
2024-10-29 10:54:57 +00:00
Andrew Ward
4280469c52
update presets more
2024-10-28 16:35:04 +00:00
Andrew Ward
3429e51c08
add presets area, working but some refinement needed
2024-10-28 16:02:28 +00:00
Andrew Ward
6670c216d2
update readme
2024-09-05 10:34:11 +01:00
Andrew Ward
c407afac5b
Update licence terms and loading into app
2024-09-05 10:28:23 +01:00
Andrew Ward
78b035823d
update version 1.0.8;
2024-08-12 15:22:17 +01:00
Andrew Ward
5dbc462d06
change .env location and add hotkey selection setting
2024-08-12 15:17:45 +01:00
