Feature: add Speech to Text in ElevenLabs API
Added
-
ElevenLabs Speech to Text Integration: Introduced Speech to Text (STT) capabilities in the ElevenLabs API integration.
- Supports transcription of audio files via URL input.
- Allows specifying:
- Model selection (e.g., scribe_v1, experimental versions).
- Language (ISO-639-1 format for accuracy and latency improvement).
- Number of Speakers for multi-speaker audio differentiation.
- Provides JSON path extraction and custom field saving for easy data handling.
Improved
- Added intuitive UI for configuring ElevenLabs STT requests.
- Supports real-time transcription testing with Test Request button.
