Haru: a low-latency, multilingual, full-duplex spoken dialogue model
☆270Nov 13, 2026Updated this week
Alternatives and similar repositories for Haru
Users that are interested in Haru are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Official repository for “GrainSpeech: Less Context, More Detail for Compact Speech Synthesis.”☆59Sep 18, 2026Updated last month
- Fast two-speaker dialogue separation: Triton and TensorRT backends for FastDialogueSidon☆26Oct 26, 2026Updated 2 weeks ago
- Faster speech off signals for spec gen voice pipelines☆91Updated this week
- Fast on-device speech enhancement for Mac, powered by RE-USE, MLX & Metal☆31Updated this week
- ☆13Aug 5, 2026Updated 3 months ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- RubatoCodec: Budgeted Adaptive Speech Tokenization with Streaming Decoding☆29Oct 30, 2026Updated 2 weeks ago
- Local LLM engine for Windows and one NVIDIA RTX 5090, built for Qwen3.8-27B☆37Updated this week
- Sophon-Realtime v1.1: open full-duplex voice models that hear your tone and speak with one. Zero-shot voice cloning, one GPU with vLLM-Om…☆321Updated this week
- Unofficial NVIDIA RE-USE speech enhancement for Apple Silicon, with a Swift SDK and iPhone/Mac samples☆18Nov 3, 2026Updated last week
- Web demo for Solv3R (3D looped transformer multi-view solver): live solves, solver lab, Gaussian splats with SHARP + gsplat☆25Updated this week
- ☆11Updated this week
- ☆44Updated this week
- ☆98Updated this week
- caramel-1, a full-duplex speech-to-speech model trained only on audio☆31Updated this week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Fast singing-voice acoustic model: harmonic + noise excitation refined into a mel by a 1-step rectified flow (bundled NHVSing vocoder). M…☆77Nov 7, 2026Updated last week
- This is not remotely close to a finished product, and does not intend to nor does this claim to be working fine-tuning code for MaskGCT. …☆13Dec 4, 2024Updated last year
- OpenAI-compatible speech serving in Rust: streaming TTS and full-duplex voice over GPT-Live. 128 concurrent PersonaPlex sessions on one G…☆51Sep 30, 2026Updated last month
- [ACL 2026] VoxMind: An End-to-End Agentic Spoken Dialogue System☆46Jul 8, 2026Updated 4 months ago
- ☆57Updated this week
- Causal zero-shot voice conversion at 44.1kHz.☆30Jul 3, 2026Updated 4 months ago
- Fast Qwen3.8-27B for one RTX 3090. 200k context, 100+ tok/s. Custom CUDA decode engine, OpenAI-compatible API.☆41Updated this week
- Project page for ScenA: Reference-Driven Multi-Speaker Audio Scene Generation from In-the-Wild Priors☆45Updated this week
- AI based singing voice synthesis☆37Jun 10, 2024Updated 2 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- ☆73Jun 11, 2026Updated 5 months ago
- singing voice conversion without f0☆22May 10, 2023Updated 3 years ago
- DuplexJev-32B and DuplexJev-4B: speech decision models for full-duplex voice agents. Typed single-token readout from a frozen speech LLM,…☆135Updated this week
- Ultra-tiny 2.1k streaming voice activity detector (2.1 KB INT8). 200 ms window for microcontrollers, edge devices, and DSPs. ships with O…☆65Sep 9, 2026Updated 2 months ago
- 559 K パラメータの日本語 TTS を ESP32-S3 で実時間合成。漢字かな交じり文の形態素解析・アクセント推定まで端末内で走る（M5Stack CoreS3 実機で確認）。推論は依存ゼロの C99、ブラウザ demo あり。arXiv:2608.21378 san…☆71Nov 2, 2026Updated last week
- A playground for experimenting with acoustic echo cancellation using a microphone, speaker, and ONNX.☆13Oct 22, 2024Updated 2 years ago
- A desktop app that transcribes and translates any audio playing on your PC in real time and shows the result as an overlay of subtitles.☆64Updated this week
- Singing voice conversion built on LeapSinger's harmonic excitation and rectified flow: content + F0 + loudness -> mel -> NHVSing. Quality…☆24Oct 1, 2026Updated last month
- balbal: Turkish speech recognition (inference, normalizer and training code)☆23Updated this week
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Pico Voice Studio - a runner and api for Emperos PiVo models☆19Nov 2, 2026Updated last week
- Speech synthesis, speech recognition and voice activity detection for voice conversation, in C++ on ggml: Qwen3-TTS, Irodori-TTS, Qwen3-A…☆408Updated this week
- ☆128Updated this week
- X-VC: Zero-shot Streaming Voice Conversion in Codec Space☆85May 6, 2026Updated 6 months ago
- VITS2 using Phoneme-Level Japanese BERT☆14Dec 17, 2023Updated 2 years ago
- Make any agent harness token-native.☆72Updated this week
- Phoneme alignment based on a variational autoencoder (VAE) and self-supervised learning (SSL) acoustic features.☆43Aug 24, 2026Updated 2 months ago
Are these results useful?