kyutai-labs / hibikiView external linksLinks
Hibiki is a model for streaming speech translation (also known as simultaneous translation). Unlike offline translation—where one waits for the end of the source utterance to start translating--- Hibiki adapts its flow to accumulate just enough context to produce a correct translation in real-time, chunk by chunk.
☆1,388Apr 15, 2025Updated 10 months ago
Alternatives and similar repositories for hibiki
Users that are interested in hibiki are comparing it to the libraries listed below
Sorting:
- Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audi…☆9,642Updated this week
- Kyutai with an "eye"☆237Mar 26, 2025Updated 10 months ago
- ☆129Jun 26, 2025Updated 7 months ago
- Interface for OuteTTS models.☆1,424Jun 21, 2025Updated 7 months ago
- Towards Human-Sounding Speech☆5,944Dec 5, 2025Updated 2 months ago
- A fast multimodal LLM for real-time voice☆4,350Dec 12, 2025Updated 2 months ago
- Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.☆2,842Jan 26, 2026Updated 3 weeks ago
- Zonos-v0.1 is a leading open-weight text-to-speech model trained on more than 200k hours of varied multilingual speech, delivering expres…☆7,160Mar 5, 2025Updated 11 months ago
- Unified automatic quality assessment for speech, music, and sound.☆673Jun 5, 2025Updated 8 months ago
- A Conversational Speech Generation Model☆14,491May 27, 2025Updated 8 months ago
- ☆376Oct 3, 2025Updated 4 months ago
- Proof of concept for running moshi/hibiki using webrtc☆20Feb 28, 2025Updated 11 months ago
- PyTorch implementation of Audio Flamingo: Series of Advanced Audio Understanding Language Models☆994Dec 15, 2025Updated 2 months ago
- Inference and training library for high-quality TTS models.☆5,533Dec 10, 2024Updated last year
- Fast and accurate automatic speech recognition (ASR) for edge devices☆3,142Updated this week
- MARS5 speech model (TTS) from CAMB.AI☆2,810Aug 1, 2024Updated last year
- first base model for full-duplex conversational audio☆1,773Jan 5, 2025Updated last year
- Speech To Speech: an effort for an open-sourced and modular GPT4-o☆4,456Updated this week
- StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models☆6,164Aug 10, 2024Updated last year
- A TTS model capable of generating ultra-realistic dialogue in one pass.☆19,109Nov 19, 2025Updated 2 months ago
- Local realtime voice AI☆2,429Nov 26, 2025Updated 2 months ago
- Real-time Speech-Text Foundation Model Toolkit (wip)☆252Mar 26, 2025Updated 10 months ago
- Inference code for the paper "Spirit-LM Interleaved Spoken and Written Language Model".☆926Oct 28, 2024Updated last year
- python bindings for symphonia/opus - read various audio formats from python and write opus files☆77Jan 7, 2026Updated last month
- StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.☆1,239Jun 29, 2025Updated 7 months ago
- Open source inference code for Rev's model☆435Apr 22, 2025Updated 9 months ago
- ☆1,267Jan 29, 2026Updated 2 weeks ago
- YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open☆6,021Jun 4, 2025Updated 8 months ago
- Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"☆14,079Updated this week
- LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis☆654Jan 21, 2026Updated 3 weeks ago
- A fundamental toolkit designed for music, song, and audio generation☆1,305May 20, 2025Updated 8 months ago
- The python library for real-time communication☆4,529Jan 12, 2026Updated last month
- Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.☆4,039Jan 8, 2025Updated last year
- An Open Source text-to-speech system built by inverting Whisper.☆4,553Dec 14, 2025Updated 2 months ago
- [EMNLP Main '25] LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation☆147May 18, 2025Updated 8 months ago
- ☆475May 19, 2025Updated 8 months ago
- Open Source framework for voice and multimodal conversational AI☆10,263Feb 11, 2026Updated last week
- An neural full-band audio codec for general audio sampled at 48 kHz with 7.5 kps or 4.5 kbps.☆197Jul 14, 2025Updated 7 months ago
- 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 spee…☆3,123May 19, 2025Updated 8 months ago