Skip to main content

AudioAgent

Defined in the agents module.
Rust AI Agent SDK A specialized agent for audio processing using AI models. Provides Text-to-Speech (TTS) and Speech-to-Text (STT) capabilities.

Fields

NameTypeDescription
nameStringAgent name
modelStringLLM model (e.g., “openai/tts-1”, “openai/whisper-1”)
configAudioConfigAudio configuration
verboseboolVerbose output

Methods

new

fn new() -> AudioAgentBuilder
Create a new AudioAgent builder

name

fn name(&self) -> &str
Get agent name

model

fn model(&self) -> &str
Get model

speech

fn speech(&self, text: &str, output_path: &str) -> Result<String>
Generate speech from text (placeholder - requires LLM integration) Parameters:
NameType
text&str
output_path&str

transcribe

fn transcribe(&self, audio_path: &str) -> Result<String>
Transcribe audio to text (placeholder - requires LLM integration) Parameters:
NameType
audio_path&str

Source

View on GitHub

praisonai/src/agents/mod.rs at line 110