Get cached analysis results

Get cached webpage content

Handle OpenAI API errors with detailed logging

* Check if audio buffer has sufficient content for transcription * @param {Buffer} audioBuffer - Audio buffer to check * @returns {boolean} True

Convert HTML to markdown with custom options

* Initialize LLM provider based on configuration

* Initialize ASR provider based on configuration

* Initialize the Silero VAD ONNX model

Load last saved checkpoint if exists

从JSON文件加载测试用例

* Process audio chunk and detect voice activity using Silero VAD * @param {Buffer} audioChunk - Raw audio data * @returns {Promise<Array>} VAD r

* Process audio chunk through VAD * @param {Buffer} audioChunk - Raw audio data

* Process speech segment with STT * @param {Buffer} audioData - Speech audio data * @param {number} duration - Duration of speech in ms

Process a batch of sources

重置内部缓冲区

Review a single slide for quality and accuracy

* Run Silero VAD inference on audio chunk * @param {Float32Array} audioSamples - Normalized audio samples * @returns {Promise<number>} Speech pr

运行验证测试

Save current execution state

Show detailed error message with traceback