Orpheus-3b-Kaya-FP16.gguf Open-Source Text-to-Speech Model - Efficient Inference Transforms Text into Sound Instantly

Orpheus 3b Kaya FP16.gguf

Developed by lex-au

A text-to-speech (TTS) model fine-tuned from Canopy Labs' pre-trained model, quantized in GGUF FP16 format for efficient inference

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

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

English Text-to-Speech

24kHz Audio Generation

Efficient Inference

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

Property	Details
Model Type	Text - to - Speech (TTS)
Architecture	Token - to - audio language model
Parameters	~3 billion
Quantisation	8 - bit GGUF (FP16)
Sampling Rate	24kHz mono
Training Epochs	1
Training Data	lex-au/Orpheus-3b-Kaya
Languages	English

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base