Expand description
§AutoAgents Speech
Speech (TTS/STT) provider abstractions for the AutoAgents framework.
This crate provides trait-based abstraction layers for speech providers, allowing different backends to be used interchangeably within the AutoAgents ecosystem.
§Features
§TTS (Text-to-Speech)
- Speech Generation: Generate audio from text
- Voice Management: Use predefined voices
- Streaming Support: Optional streaming for real-time audio generation
- Model Management: Support for multiple models and languages
§STT (Speech-to-Text)
- Transcription: Convert audio to text
- Streaming Support: Real-time audio transcription
- Timestamp Support: Token-level timestamps for transcriptions
- Multilingual: Support for multiple languages with auto-detection
§Architecture
The crate follows a trait-based design with provider implementations in the providers module:
§TTS Traits
TTSProvider: Marker trait combining all TTS capabilitiesTTSSpeechProvider: Speech generation capabilitiesTTSModelsProvider: Model and language support
§STT Traits
STTProvider: Marker trait combining all STT capabilitiesSTTSpeechProvider: Transcription capabilitiesSTTModelsProvider: Model and language support
§Providers
Enable providers using feature flags:
pocket-tts: Pocket-TTS model support (TTS)parakeet: Parakeet (NVIDIA) model support (STT)vad: Silero VAD support (speech segmentation)
Re-exports§
pub use error::TTSError;pub use error::TTSResult;pub use tts::ChunkerConfig;pub use tts::SentenceChunker;pub use tts::StreamingTtsPipeline;pub use types::AudioChunk;pub use types::AudioData;pub use types::AudioFormat;pub use types::ModelInfo;pub use types::SpeechRequest;pub use types::SpeechResponse;pub use types::VoiceIdentifier;pub use error::STTError;pub use error::STTResult;pub use model_source::ModelSource;pub use types::TextChunk;pub use types::TokenTimestamp;pub use types::TranscriptionRequest;pub use types::TranscriptionResponse;
Modules§
- error
- model_
source - providers
- Speech provider implementations
- tts
- TTS utilities for sentence chunking and streaming pipeline.
- types
Traits§
- STTModels
Provider - Trait for STT model management capabilities
- STTProvider
- Marker trait for STT providers
- STTSpeech
Provider - Trait for STT transcription capabilities
- TTSModels
Provider - Trait for TTS model management capabilities
- TTSProvider
- Marker Trait for TTS providers
- TTSSpeech
Provider - Trait for TTS speech generation capabilities