AudioTraceFlavorConfig

class AudioTraceFlavorConfig ( BaseTraceFlavorConfig )

Audio trace flavor configuration for STT benchmarking.

Polymorphic Type:

type: audio

All BaseTraceFlavorConfig types:

• timed_synthetic_session: TimedSyntheticSessionTraceFlavorConfig

• shared_prefix: SharedPrefixTraceFlavorConfig

• rag: RAGTraceFlavorConfig

• request_log: RequestLogTraceFlavorConfig

• untimed_content_multi_turn: UntimedContentMultiTurnTraceFlavorConfig

• sharegpt: ShareGPTTraceFlavorConfig

• audio: AudioTraceFlavorConfig

• seed_tts_text: SeedTTSTextTraceFlavorConfig

Fields:

audio_dirstr = ""

Optional base directory prepended to relative audio_file paths.

target_duration_sOptional [ float ] = None

Optional per-session audio duration to stream. The trace must provide reference_word_timestamps so expected transcripts can be trimmed to the streamed prefix.

target_duration_spread_sOptional [ float ] = None

Hard half-width of a clipped-Gaussian duration spread around target_duration_s. Requires target_duration_s.

target_duration_sigma_sOptional [ float ] = None

Standard deviation of the clipped-Gaussian duration draw. Defaults to half the spread and must not exceed the spread.