aicuflowDocsTool How-ToAI Model InferenceAudioAudio InferenceSpeech recognition and audio processing modelsAudio inference models process sound inputs and produce text or structured data. ASR (Automatic Speech Recognition) – Transcribe spoken audio to text PaddleOCR-VLVision-language OCR with handwriting support, table-to-HTML, and prompt-based extractionAutomatic Speech RecognitionTranscribe spoken audio to text using speech recognition models