- Integrate local Piper ONNX neural TTS engine (Dmitri, Irina, Denis, Ruslan) - Add GET /api/radio/preview-voice endpoint with cached pre-rendered samples - Add '▶ Прослушать голос' button in Web UI for 1-click preview before generating - Add automated filter to strip LLM refusals and fall back to clean radio phrasing
17 lines
297 B
Plaintext
17 lines
297 B
Plaintext
fastapi>=0.110.0
|
|
uvicorn[standard]>=0.30.0
|
|
pydantic>=2.7.0
|
|
pydantic-settings>=2.4.0
|
|
yandex-music>=3.2.0
|
|
yt-dlp>=2024.10.0
|
|
mutagen>=1.47.0
|
|
syncedlyrics>=0.10.0
|
|
aiofiles>=24.1.0
|
|
httpx>=0.27.0
|
|
jinja2>=3.1.0
|
|
python-multipart>=0.0.12
|
|
spotifyscraper>=3.9.0
|
|
edge-tts>=6.1.12
|
|
gtts>=2.5.0
|
|
piper-tts>=1.2.0
|