Projects sharing features with Kimi Audio

VoxCPM is a multilingual speech synthesis system and text-to-speech inference server. It functions as an AI voice cloning tool and a synthetic voice designer, capable of generating natural speech across global languages and regional dialects using a GPU-accelerated audio generator. The project features a speech model fine-tuning framework that supports both full parameter updates and low-rank adaptation for customizing voice characteristics. It enables high-fidelity voice cloning from reference audio, including cross-lingual voice transfer and acoustic environment mimicry, as well as the crea

PaddleSpeech is a comprehensive toolkit of neural models for speech recognition, synthesis, and translation built on the PaddlePaddle deep learning framework. It provides a collection of frameworks and tools for converting spoken audio into written text, synthesizing natural audio from text, and performing direct speech translation. The toolkit includes specialized capabilities for keyword spotting to detect trigger words and speaker verification systems that extract unique voiceprints to identify and distinguish between individuals. It also features end-to-end translation tools that map audi

jetson-inference is a set of libraries and tools for executing optimized deep learning models on embedded GPU hardware. Its primary purpose is to enable real-time computer vision and AI inference at the edge with low latency and high throughput. The project distinguishes itself through high-performance streaming analytics and the ability to execute concurrent AI pipelines on auto-grade silicon. It provides specialized support for multi-sensor stream processing, utilizing zero-copy data transport to load camera frames directly into GPU memory. The codebase covers a broad surface of capabiliti

This project is a deep learning text-to-speech toolkit used for training and deploying neural speech synthesis models. It provides a comprehensive framework for converting written text into spoken audio, utilizing neural vocoders to transform synthesized spectrograms into high-fidelity audio waveforms. The toolkit includes a voice cloning system that replicates specific human voices by extracting speaker embeddings from short audio samples. It also supports multi-speaker audio synthesis, allowing the generation of speech across different vocal identities using specialized model architectures.

Qwen2.5-Omni is an omnichannel multimodal large language model designed to process and generate content across text, audio, vision, and video. It functions as a real-time speech AI, utilizing an end-to-end architecture to maintain synchronous voice conversations with low-latency responses. The project emphasizes efficiency through quantized edge models, allowing for local inference on mobile hardware and resource-constrained devices. It employs 4-bit weight quantization, CPU-based process offloading, and on-demand weight loading to reduce GPU memory requirements. The system integrates specia

Linly-Dubbing is an automated video dubbing pipeline designed for multilingual video localization. It converts spoken content in videos into another language by coordinating speech-to-text transcription, text translation, and text-to-speech synthesis. The system distinguishes itself through AI-driven lip synchronization and animation, which aligns facial expressions and mouth movements to the synthesized voiceover. It also utilizes audio source separation to isolate vocals from background music and noise, allowing for clean voice replacement while preserving original background audio. The br

mlx-audio is an audio processing toolkit built on Apple MLX that provides speech transcription, text-to-speech synthesis, voice cloning, and audio source separation using local models. It offers an OpenAI-compatible REST API and web interface for running audio generation and transcription tasks, enabling drop-in integration with existing tools that follow that endpoint structure. The toolkit supports text-prompted audio source separation, allowing specific sounds to be isolated from mixed recordings based on natural language descriptions. It also provides voice cloning from a short reference

Pipecat is a framework and software development kit for building real-time multimodal AI agents and speech-to-speech systems. It utilizes a frame-based data pipeline to route audio, video, and text through a modular sequence of processors, enabling the orchestration of low-latency conversational AI. The project is distinguished by its ability to coordinate complex multimodal services, including speech-to-text, language models, and text-to-speech, within a single pipeline. It features semantic voice activity detection for natural turn-taking, state-machine conversation flows for dialogue manag

Amphion is an audio generation toolkit designed for the research and development of models that synthesize speech, music, and environmental sound effects. It provides a standardized framework for reproducible audio synthesis, incorporating a text-to-speech engine and a voice conversion framework. The project specializes in transforming audio identities, allowing for the modification of speaker accents and voice identities while preserving original rhythm and style. It also includes capabilities for singing voice synthesis and the generation of environmental soundscapes from text descriptions

This project is a framework for developing multimodal AI agents that function as programmable participants in real-time communication rooms. It enables the construction of agents that can see, hear, and speak by integrating speech-to-text, large language models, and text-to-speech pipelines to facilitate low-latency, natural conversations. The system is distinguished by its advanced orchestration of real-time media and conversational flow, including support for full-duplex speech, preemptive response generation, and sophisticated interruption management. It further differentiates itself throu

This project is a TensorFlow implementation of a neural network for raw audio waveform generation. It functions as a conditioned speech synthesis model that produces synthetic audio samples using a dilated convolutional neural network architecture. The system supports custom voice modeling by incorporating global conditioning and categorical identifiers during training and generation. This allows the model to mimic specific speakers or distinct audio characteristics for neural text-to-speech applications. The framework covers deep learning audio synthesis, including audio dataset processing,

Fonoster is a conversational AI framework and multi-tenant communications platform as a service. It serves as a programmable voice gateway and SIP telephony platform, enabling the creation of voice-based assistants and automated communication workflows using large language models. The project distinguishes itself through a vendor-agnostic speech integration engine that abstracts speech-to-text and text-to-speech providers. It features a multi-tenant architecture that isolates telephony resources and user identities into distinct organizational workspaces. The system covers a broad range of t

Streamer-Sales is a digital avatar video generator and large language model sales agent framework. It functions as a multimodal AI pipeline that synthesizes talking-head videos using text-to-speech and face animation to create virtual spokespeople. The system differentiates itself by combining retrieval-augmented generation with agentic web searching to ground product descriptions and sales scripts in factual data and real-time information. It further integrates a multimodal interaction workflow that coordinates automatic speech recognition and text-to-speech for real-time voice conversations

Neutts is a neural text-to-speech engine designed for real-time streaming output on edge devices such as phones and laptops. It supports voice cloning from short audio references, enabling zero-shot reproduction of a target speaker's voice, and can be fine-tuned or retrained from scratch for custom voices and styles. The system distinguishes itself through a decoder-only architecture that halves memory and accelerates generation on constrained hardware, combined with quantized model inference for reduced memory footprint. Its streaming decoder loop interleaves synthesis with playback, deliver

VibeVoice is a generative artificial intelligence platform designed for text-to-speech synthesis. It functions as a neural audio generation framework that converts written text into natural-sounding spoken audio, specifically engineered to maintain consistent vocal characteristics and narrative prosody across extended passages of content. The system distinguishes itself through its ability to generate long-form conversational speech while preserving speaker identity and linguistic content. By utilizing latent space disentanglement, the model separates speaker traits from the input text, allow

Chatterbox is a comprehensive machine learning platform designed for multilingual speech synthesis and real-time audio generation. It functions as an engine that converts text into natural-sounding speech, capable of replicating specific human vocal characteristics and emotional expressions from short audio samples. The platform distinguishes itself through advanced control over the synthesis process, allowing for the manipulation of emotional intensity and the injection of non-verbal vocalizations such as laughter or coughing. It is engineered for low-latency performance, utilizing an optimi

Torchtune is a PyTorch-native library for fine-tuning, aligning, and quantizing large language models. It provides a config-driven system for instantiating components, orchestrating distributed training, and managing parameter-efficient fine-tuning with quantization support, all through YAML-based configurations and command-line overrides. The library distinguishes itself through its comprehensive post-training workflow orchestration, combining supervised fine-tuning, preference optimization (DPO, PPO, GRPO), knowledge distillation, and quantization-aware training in a single configurable pip

Whisper Real-Time is a speech-to-text engine designed to convert continuous microphone input into written transcripts. It functions as a real-time audio processor that leverages the OpenAI Whisper model to generate immediate textual output from live spoken language. The system utilizes a transformer-based architecture to map audio sequences to text tokens. It manages incoming data through a sliding-window buffering mechanism and a circular buffer, which ensures a steady stream of audio for the inference engine. To maintain accuracy during continuous processing, the software employs a stateful

KittenTTS is a neural text-to-speech engine and text-to-audio synthesis tool that converts written text into spoken audio using lightweight neural network models. It functions as both a speech synthesizer and an audio file generator, producing spoken audio for offline playback. The system includes a text normalization processor that expands numbers and abbreviations into full spoken words to improve the naturalness of the synthesized speech. It supports diverse voice options and provides the ability to adjust playback speed.

Xiaogpt is a voice-activated interface and bridge that connects large language models to smart speakers, specifically providing integration for Xiaomi hardware. It functions as a gateway that routes voice queries from hardware microphones to external language model providers and converts the resulting text into audible speech. The system enables the replacement of default smart speaker logic with custom AI models and prompt behaviors. It supports real-time information retrieval by integrating search APIs, allowing the assistant to provide current internet data through spoken responses. The p

ChatTTS is a conversational text-to-speech generative model designed to convert written dialogue into natural sounding audio. It functions as a multilingual speech synthesis framework capable of producing human-like audio across different languages and speaker profiles. The system is distinguished by its ability to generate interactive dialogue with realistic vocal nuances. It utilizes a speech nuance controller to insert specific tokens that trigger non-verbal elements, such as laughter, pauses, and interjections, during the synthesis process. The project includes a streaming audio generato

RealtimeVoiceChat is a conversational AI gateway and voice chat interface that enables real-time spoken interactions with large language models. It functions as a streaming audio pipeline that integrates speech-to-text transcription and text-to-speech synthesis to facilitate natural voice conversations. The system utilizes WebSocket-based audio streaming and an asynchronous text-to-speech pipeline to maintain low latency. It includes specialized conversational controls such as silence-based turn detection and client-side interrupt handling, which stops active audio playback when new user spee

OpenVoice is a multilingual text-to-speech framework and voice cloning AI model designed for high-fidelity voice replication and low-latency audio generation. It functions as an instant speech synthesis engine that converts text to audio while replicating a specific speaker's tone and color. The system is distinguished by its ability to perform cross-lingual cloning, allowing the vocal characteristics of a reference speaker to be applied to speech in different languages regardless of the original training data. It utilizes a decoupled representation to separate the physical identity of a voic

Index-tts is a neural audio generation engine designed to convert written text into high-fidelity human speech. By utilizing deep learning models and phoneme-based sequence modeling, the system transforms text into natural-sounding audio waveforms suitable for a variety of accessibility and media applications. The platform functions as a server-side inference pipeline that provides a programmatic interface for integrating voice generation into external applications. It distinguishes itself through asynchronous audio streaming, which buffers and delivers generated speech chunks in real time to

Fairseq is a PyTorch toolkit for sequence-to-sequence modeling, specializing in neural machine translation, automatic speech recognition, and large-scale language model training. It provides a framework for processing and aligning diverse data sources, including text, audio, and video, to support tasks such as speech-to-text conversion and multimodal sequence learning. The project is distinguished by its distributed training capabilities, which utilize parameter sharding, mixed-precision training, and CPU offloading to handle models that exceed single-device memory. It also includes specializ