Orpheus 3b Kaya FP16.gguf
A text-to-speech (TTS) model fine-tuned from Canopy Labs' pre-trained model, quantized in GGUF FP16 format for efficient inference
Speech Synthesis Supports Multiple LanguagesOpen Source License:Apache-2.0#Efficient Speech Synthesis#Low-Resource Inference#English TTS
Downloads 45
Release Time : 4/19/2025
Model Overview
This is a 3-billion-parameter text-to-speech model, fine-tuned and quantized in GGUF format, supporting English speech synthesis
Model Features
Efficient Quantization
Utilizes GGUF FP16 quantization format for fast and efficient inference
High-Quality Speech Synthesis
Fine-tuned from a 3-billion-parameter model, generating 24kHz sampled mono audio
Strong Compatibility
Supports multiple inference platforms including GPUStack, LM Studio, and llama.cpp
Model Capabilities
English Text-to-Speech
24kHz Audio Generation
Efficient Inference
Use Cases
Speech Synthesis Applications
Voice Assistants
Provides natural speech output for smart assistants
Generates natural and fluent speech responses
Audiobooks
Converts text content into speech
Produces high-quality narration audio
Featured Recommended AI Models