# Lightweight TTS

A text-to-speech model fine-tuned based on Orpheus-3B, supporting the conversion of text into natural and fluent speech

Dia 1.6B is a model suitable for text-to-speech tasks, supporting multiple quantized versions and compatible with the TTS.cpp framework.

Spark-TTS-0.5B-4-6bit is a text-to-speech model based on the MLX format, supporting both English and Chinese.

Spark-TTS-0.5B-fp16 is a text-to-speech model based on the MLX format, supporting both English and Chinese.

OuteTTS is a text-to-speech (TTS) model focused on the Turkish language, based on a 500M parameter scale, capable of converting Turkish text into natural speech.

A Japanese TTS model trained on sarashina2.2‑0.5b‑instruct‑v0.1, supporting quality control via prompts

A lightweight version of StyleTTS 2, focused on text-to-speech tasks, with multiple components removed to reduce complexity.

A fine-tuned text-to-speech model based on Canopy Labs' pre-trained model, quantized for efficient inference

Kokoro is a text-to-speech (TTS) model offering GGUF-encoded versions with dual phonemization support.

This is a German text-to-speech model based on MLX format conversion, supporting German language processing tasks.

This model is a proof-of-concept fine-tuned version of the Orpheus 3B TTS (Text-to-Speech) model to support Bengali.

Fine-tuned version of Orpheus 3B TTS model for Bengali, trained with 955 audio samples, suitable for experimental Bengali speech synthesis

CiSiMi is an early prototype of a text-to-audio model designed for resource-constrained environments and capable of efficient operation on the CPU to achieve advanced speech synthesis.

Kokoro is an open-source text-to-speech model with 82 million parameters, delivering sound quality comparable to large models through a lightweight architecture while significantly improving speed and cost efficiency.

Kokoro is an open-weight series of small yet powerful text-to-speech (TTS) models, now featuring data from 100 Chinese speakers sourced from professional datasets.

Kokoro is an open-source TTS model with 82 million parameters, delivering audio quality comparable to larger models while offering significant speed advantages and cost efficiency.

Kokoro is an open-source text-to-speech model with 82 million parameters, achieving sound quality comparable to large models with a lightweight architecture while improving generation speed and reducing computational costs.

A clone version based on StyleTTS2-LJSpeech, optimized for English text-to-speech tasks with reduced dependencies for simplified deployment.

Kokoro is a cutting-edge text-to-speech (TTS) model with 82 million parameters, released under Apache 2.0 license. Ranked #1 in TTS Spaces Arena, achieving higher Elo scores with fewer parameters and data.

Kokoro is an open-source text-to-speech (TTS) model with 82 million parameters, renowned for its lightweight architecture and high audio quality, while also being fast and cost-effective.

GGUF format model file of Parler TTS Mini v1 for text-to-speech tasks, supporting the English language.

Indri is a novel, ultra-small, lightweight TTS model based on the Transformer architecture, supporting text-to-speech tasks in English and Hindi.

A Japanese text-to-speech model fine-tuned based on parler-tts-large-v1, capable of generating high-quality Japanese speech

Indri is an ultra-compact lightweight TTS model based on Transformer architecture, supporting English and Hindi text-to-speech tasks.

Parler-TTS Mini v1.1 is a lightweight text-to-speech model trained on 45,000 hours of audio data, capable of generating high-quality, natural-sounding speech with controllable features through simple text prompts.

Lightweight text-to-speech model trained on 45,000 hours of audio data, capable of controlling voice attributes through text prompts

Parler-TTS Mini is a lightweight text-to-speech model trained on 10.5K hours of audio data, supporting voice feature control through text prompts.

Urdu speech synthesis model fine-tuned on the fleurs dataset based on microsoft/speecht5_tts