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.
☆1,452Apr 15, 2025Updated last year
Alternatives and similar repositories for hibiki
Users that are interested in hibiki are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
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…☆10,070Updated this week
- ☆135Jun 26, 2025Updated 10 months ago
- Kyutai with an "eye"☆246Mar 26, 2025Updated last year
- Interface for OuteTTS models.☆1,428Mar 23, 2026Updated last month
- Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.☆2,905Jan 26, 2026Updated 3 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Towards Human-Sounding Speech☆6,113Dec 5, 2025Updated 4 months ago
- ☆436Oct 3, 2025Updated 6 months ago
- Unified automatic quality assessment for speech, music, and sound.☆710Jun 5, 2025Updated 10 months ago
- Proof of concept for running moshi/hibiki using webrtc☆21Feb 28, 2025Updated last year
- A fast multimodal LLM for real-time voice☆4,404Dec 12, 2025Updated 4 months 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…☆7,193Mar 5, 2025Updated last year
- A Conversational Speech Generation Model☆14,607May 27, 2025Updated 11 months ago
- StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.☆1,259Jun 29, 2025Updated 10 months ago
- Real-time Speech-Text Foundation Model Toolkit (wip)☆257Mar 26, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- An neural full-band audio codec for general audio sampled at 48 kHz with 7.5 kps or 4.5 kbps.☆204Jul 14, 2025Updated 9 months ago
- PyTorch implementation of Audio Flamingo: Series of Advanced Audio Understanding Language Models☆1,110Dec 15, 2025Updated 4 months ago
- python bindings for symphonia/opus - read various audio formats from python and write opus files☆79Jan 7, 2026Updated 3 months ago
- Local realtime voice AI☆2,483Nov 26, 2025Updated 5 months ago
- Inference and training library for high-quality TTS models.☆5,567Dec 10, 2024Updated last year
- A TTS model capable of generating ultra-realistic dialogue in one pass.☆19,288Nov 19, 2025Updated 5 months ago
- MARS5 speech model (TTS) from CAMB.AI☆2,813Aug 1, 2024Updated last year
- first base model for full-duplex conversational audio☆1,784Jan 5, 2025Updated last year
- Inference code for the paper "Spirit-LM Interleaved Spoken and Written Language Model".☆930Oct 28, 2024Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open☆6,177Jun 4, 2025Updated 10 months ago
- ☆476May 19, 2025Updated 11 months ago
- Make text LLMs listen and speak☆1,280Mar 26, 2026Updated last month
- Build local voice agents with open-source models☆4,693Updated this week
- StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models☆6,243Aug 10, 2024Updated last year
- Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"☆14,404Apr 20, 2026Updated last week
- ☆1,354Jan 29, 2026Updated 3 months ago
- Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces☆7,870Updated this week
- The python library for real-time communication☆4,580Jan 12, 2026Updated 3 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Foundational Models for State-of-the-Art Speech and Text Translation☆11,770Apr 8, 2026Updated 3 weeks ago
- A fundamental toolkit designed for music, song, and audio generation☆1,338May 20, 2025Updated 11 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…☆3,139May 19, 2025Updated 11 months ago
- Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.☆4,074Jan 8, 2025Updated last year
- [TACL'26] VoiceBench: Benchmarking LLM-Based Voice Assistants☆356Updated this week
- A family of state-of-the-art Transformer-based audio codecs for low-bitrate high-quality audio coding.☆425Feb 12, 2026Updated 2 months ago
- [ICLR 2025] SOTA discrete acoustic codec models with 40/75 tokens per second for audio language modeling☆1,290Mar 2, 2025Updated last year