vox-speech API Reference (generated)

vox-speech

Crate: vox-speech · Version: 0.6.0 · Target: Library (lib.rs)

Vox speech-to-text (Oratio) — transcript refinement, routing and Sherpa-ONNX STT; Candle Whisper lives in vox-plugin-speech

Crate Overview

Oratio — Vox speech-to-text and transcript refinement.

STT runs through Sherpa-ONNX in-process (stt-sherpa) or Candle Whisper in the oratio plugin (vox-plugin-speech), which hosts register through [backend_dispatch::register_whisper_transcriber]. Audio file decoding needs the audio-decode feature; without it only .txt / .md passthrough is available.

Features

Feature	Default / Enables
audio-decode	dep:symphonia, dep:rubato
cloud	dep:vox-populi, dep:tokio, dep:vox-http-client, dep:async-trait, dep:reqwest
compiler-rerank	dep:vox-compiler
default	compiler-rerank
serve	dep:axum, axum/multipart, dep:tokio
stt-sherpa	dep:sherpa-onnx, dep:hf-hub, audio-decode

Workspace Dependencies

Dependency	Kind
vox-compiler	Normal
vox-config	Normal
vox-http-client	Normal
vox-populi	Normal
vox-secrets	Normal

Public API Surface

Modules

Module	Description
acoustic_preprocess	—
ast_mapper	—
contextual_bias	—
backend_dispatch	—
backends	—
eval	—
eval_srt	—
failure_taxonomy	—
refine	—
routing	—
session	—
speaker_profile	—
speech_intent	—
speech_lexicon	—
speech_normalize	—
speech_policy	—
streaming_partial	Env-tunable stabilization thresholds for future streaming decoders; offline transcribe_path ignores this.
subtitle	—
tiering	Policy helpers (escalation hint, cache keys) for hosts — not required for file-based STT.
trace	—
traits	—
transcript_rerank	—
vad	—
serve	—

Functions

Function	Description
candle_backend_status_json	JSON status for the in-process Candle backend — always {"stt_candle": false}: Candle Whisper runs in the oratio plugin (vox-plugin-speech).