1. Configure & Input

? Keyboard Mode:

- When enabled, you can press Enter to generate speech.

- Pressing Shift+Enter will insert a newline.
1.0x

Available APIs

POST /tts/audio/speech ? Input:
- JSON body with `input`, `voice`, and `speed`.

Output:
- Audio file in WAV format.

Authentication:
- Bearer Token in Authorization header.

GET /tts/audio/voices ? Output:
- JSON: `["voice1", "voice2", ...]`

POST /transcribe ? Input:
- File sent as multipart/form-data.
- Supported formats: wav, mp3, flac, ogg.

Output:
- JSON: `{"text": "your transcribed text"}`

Authentication:
- Bearer Token in Authorization header.

POST /api/translate ? Input:
- JSON body with `text` and `language`.
- `model` is optional.

Output:
- JSON: `{"translated_text": "your translated text"}`

Authentication:
- Bearer Token in Authorization header.