🎙️ Whisper Large v3 Turbo

Streaming Speech-to-Text

Real-time transcription with OpenAI Whisper Large v3 Turbo

Model: - Status: Disconnected

🔌 Connection

Server URL:

Language: Temperature:

Buffer Duration: Silence Flush VAD 🔇 Noise Filter (DeepFilterNet) VAD Threshold:

Initial Prompt (Optional - helps with specific words/names):

Duration: 0.00s Audio Sent: 0 KB Segments: 0 Language Detected: -

Connect, then record or upload audio. Transcription will appear here...