A Flow Matching-based Text-to-Speech Model with Emoji-driven Style Control

PersonaPlex code.

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!

Faster Whisper transcription with CTranslate2

PSAP auto-tuning for vllm (vllm+guidellm+optuna)

Reverse Engineering of Supervised Semantic Speech Tokenizer (S3Tokenizer) proposed in CosyVoice

11 Lessons to Get Started Building AI Agents

LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis

Codec for paper: LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis

A curated list of resources dedicated to Python libraries, LLMs, dictionaries, and corpora of NLP for Japanese

Zonos-v0.1 is a leading open-weight text-to-speech model trained on more than 200k hours of varied multilingual speech, delivering expressiveness and quality on par with—or even surpassing—top TTS …

A simple, hackable text-to-speech system in PyTorch and MLX

zero-shot voice conversion & singing voice conversion, with real-time support

G2P

A Fast TTS Engine

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

⚡ A modern Pythonic implementation of Avro Phonetic.

Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities。

Localized watermarking for AI-generated speech audios, with SOTA on robustness and very fast detector

NeMo text processing for ASR and TTS

LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.

Official PyTorch implementation of BigVGAN (ICLR 2023)

State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz mono/stereo audio.

In this repository I will be running various experiments on finetune different parts for xtts

💎 A list of accessible speech corpora for ASR, TTS, and other Speech Technologies