DeepFellow DOCS

AudioChunkingStrategy

PropertyTypeRequiredDescription
typestringYesMust be set to 'server_vad' to enable manual chunking using server side VAD Always server_vad.
prefix_padding_msinteger | nullNoAmount of audio to include before the VAD detected speech (in milliseconds). This ensures the beginning of speech is not cut off.
silence_duration_msinteger | nullNoDuration of silence to detect speech stop (in milliseconds). With shorter values the model will respond more quickly, but may jump in on short pauses from the user.
thresholdnumber | nullNoSensitivity threshold (0.0 to 1.0) for voice activity detection. A higher threshold will require louder audio to activate the model, and thus might perform better in noisy environments.

We use cookies on our website. We use them to ensure proper functioning of the site and, if you agree, for purposes such as analytics, marketing, and targeting ads.