Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
Repository Index
47,133 repositories indexed
49–72 of 169 · Most stars
Real-time, local speech-to-text with streaming ASR, speaker diarization, translation, and OpenAI/Deepgram-compatible APIs.
- python
- real-time
- speaker-diarization
- speech-recognition
OpenVINO™ is an open source toolkit for optimizing and deploying AI inference
- inference
- deep-learning
- openvino
- ai
Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding
- pytorch
- speech-processing
- speaker-diarization
- speech-activity-detection
High-performance GPGPU inference of OpenAI's Whisper automatic speech recognition (ASR) model
:robot: :speech_balloon: Deep learning for Text to Speech (Discussion forum: https://discourse.mozilla.org/c/tts)
AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head
Speech recognition module for Python, supporting several engines and APIs, online and offline.
💬 Speech recognition for your site
- speech-recognition
- speech
- speech-to-text
- voice
Facebook AI Research's Automatic Speech Recognition Toolkit
- wav2letter
- speech-recognition
- end-to-end
- deep-learning
On-device wake word detection powered by deep learning
- wake-word-detection
- hotword
- keyword-spotting
- keyword-spotter
JAX implementation of OpenAI's Whisper model for up to 70x speed-up on TPU.
Open singing synthesis platform / Open source UTAU successor
- utau
- vocaloid
- music
- singing-synthesis
A small speech recognizer
- speech-recognition
- python
- c
State of the Art Natural Language Processing
:stuck_out_tongue_closed_eyes: TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)
- speech-synthesis
- text-to-speech
- tensorflow2
- melgan
The Swiss Army Knife of Offline AI. Chat, see, speak, and generate images on your phone or Mac — GGUF LLMs, vision, Whisper speech-to-text, Stable Diffusion, tool calling, and local-network servers. Runs on your CPU, GPU, or NPU. No account, no API key, zero data leaves your device.
- privacy-first
- gguf
- llama-cpp
- local-ai
Frontier CoreML audio models in your apps — text-to-speech, speech-to-text, voice activity detection, and speaker diarization. In Swift, powered by SOTA open source.
Data manipulation and transformation for audio signal processing, powered by PyTorch
- audio
- python
- io
- speech
aeneas is a Python/C library and a set of tools to automagically synchronize audio and text (aka forced alignment)
- speech
- alignment
- tts
- python
Multilingual Automatic Speech Recognition with word-level timestamps and confidence
Python library and CLI tool to interface with Google Translate's text-to-speech API
- speech
- python
- tts
- text-to-speech
This library provides common speech features for ASR including MFCCs and filterbank energies.
🔊 Awesome list for Whisper — an open-source AI-powered speech recognition system developed by OpenAI