Struct SpeechProcessor 

pub struct SpeechProcessor { /* private fields */ }

Core speech processor without Tauri dependencies

This processor handles:

• Audio recording with VAD
• Speech-to-text transcription
• LLM processing

Event emission and window management should be handled by the caller.

Implementations

impl SpeechProcessor

pub fn new() -> SpeechProcessor

Create a new speech processor with default configuration

pub fn with_config(config: SpeechConfig) -> SpeechProcessor

Create a new speech processor with custom configuration

pub fn update_config(&self, config: SpeechConfig)

Update the speech processor configuration

pub fn get_config(&self) -> SpeechConfig

Get the current configuration

pub fn is_recording(&self) -> bool

Check if currently recording

pub fn set_recording(&self, recording: bool)

Set recording state

pub fn stop_recording(&self) -> Result<(), AppError>

Stop the current recording

pub async fn record_audio_to_file( &self, device_name: Option<String>, ) -> Result<(f32, PathBuf), AppError>

Record audio from microphone and return the path to the audio file

Returns the duration and path to the recorded audio file. The caller is responsible for cleaning up the temp file.

pub fn is_conversation(&self, text: &str) -> bool

Determine if text is a conversation or command

Trait Implementations

impl Clone for SpeechProcessor

fn clone(&self) -> SpeechProcessor

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for SpeechProcessor

fn fmt(&self, f: &mut Formatter<'_>) -> Result<(), Error>

Formats the value using the given formatter.

impl Default for SpeechProcessor

fn default() -> SpeechProcessor

Returns the “default value” for a type.

impl SpeechProcessorCoreExt for SpeechProcessor

fn transcribe_audio<'life0, 'life1, 'async_trait>( &'life0 self, audio_path: &'life1 Path, ) -> Pin<Box<dyn Future<Output = Result<TranscriptionResult, AppError>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

Transcribe audio file to text using core-owned STT provider selection.

fn process_with_llm<'life0, 'life1, 'async_trait>( &'life0 self, text: &'life1 str, ) -> Pin<Box<dyn Future<Output = Result<LlmResponse, AppError>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

Process transcribed text with configured LLM provider.