SAVA, semantic acoustic voice activity: streaming voice activity and end-of-turn detection in one model.
☆46Nov 18, 2026Updated this week
Alternatives and similar repositories for sava
Users that are interested in sava are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Voice isolation — separating clean speech from background noise and mixed audio.☆121Updated this week
- ☆13Oct 28, 2026Updated 3 weeks ago
- Fast two-speaker dialogue separation: Triton and TensorRT backends for FastDialogueSidon☆39Oct 26, 2026Updated 3 weeks ago
- ☆10Jul 31, 2026Updated 3 months ago
- Residual emotion steering for emotional TTS generation. EmoRES-TTS decomposes a mixed-emotion steering vector into a shared axis and an e…☆45Oct 1, 2026Updated last month
- 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.
- System-One-controlled full-duplex voice interaction: turn-taking as plain-language decisions judged by Jev.☆71Updated this week
- ☆14Jun 24, 2026Updated 4 months ago
- ☆14Jun 3, 2026Updated 5 months ago
- Decoupling Voice Design from Speech Generation in Instruction-Following TTS☆16Oct 15, 2026Updated last month
- ☆25Updated this week
- ConversationalVoice: Full-Duplex Speech Data from Real Conversations☆87Sep 18, 2026Updated 2 months ago
- ☆52Apr 27, 2026Updated 6 months ago
- ☆32Nov 11, 2026Updated last week
- A simple command line tool to calculate WER for ASR.☆15Jul 28, 2026Updated 3 months ago
- 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.
- ☆25Oct 19, 2026Updated last month
- Research about Voxtral, its codebooks and an attempt to reconstruct codes for a known audio☆13Apr 6, 2026Updated 7 months ago
- ☆11Sep 16, 2025Updated last year
- MSRCodec demo☆14Feb 24, 2026Updated 8 months ago
- ☆11Oct 14, 2023Updated 3 years ago
- AmphionASR: Personalized Context-Aware Speech Recognition☆14Jul 28, 2026Updated 3 months ago
- A repository for Automatic Speech Recognition (ASR) that ensembles multiple open-source models to achieve SOTA quality of recognition. Us…☆23Jul 28, 2026Updated 3 months ago
- VoxCanvas-41M: A Large-Scale Bilingual Dataset for Instruction-Based Speech Editing and Its Learning Dynamics☆35Nov 9, 2026Updated last week
- [ACL 2026] Dual-Axis Generative Reward Model Toward Semantic and Turn-taking Robustness in Interactive Spoken Dialogue Models☆22May 23, 2026Updated 5 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Unifying General Audio Understanding and Spatial Awareness☆58Oct 15, 2026Updated last month
- DuplexJev-32B and DuplexJev-4B: speech decision models for full-duplex voice agents. Typed single-token readout from a frozen speech LLM,…☆148Nov 8, 2026Updated last week
- Official implementation of “Learning Where to Split: Dynamic Band Splitting for Audio Source Separation”☆37Oct 15, 2026Updated last month
- ☆64Jul 5, 2026Updated 4 months ago
- ☆30Sep 9, 2026Updated 2 months ago
- Official repository for NVMOS: Non-Verbal Vocalization Quality Assessment in Speech☆26Jun 16, 2026Updated 5 months ago
- A solution to denoising and separating for two-speaker-mixed noisy speech, using a BSRNN inspired network.☆15Aug 22, 2023Updated 3 years ago
- ☆19Nov 19, 2025Updated last year
- ☆14Mar 18, 2026Updated 8 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- A toolkit for researchers in the multimodal sound separation.☆16Oct 20, 2023Updated 3 years ago
- Agent skill (Claude Code / Codex) for condensing, typesetting and fact-checking a LaTeX paper to ICASSP's 4+1 page limit, verified by mea…☆19Sep 14, 2026Updated 2 months ago
- ☆23Sep 14, 2025Updated last year
- Eureka-Audio: A 1.7B lightweight audio–language model that matches 7B–30B models on ASR, audio understanding, and paralinguistic reasonin…☆50Apr 11, 2026Updated 7 months ago
- ☆200Sep 11, 2026Updated 2 months ago
- An AI-powered meeting experience built with Agora and OpenAI GPT-Live-1 that can listen, respond, summarize, and take action in real time…☆11Sep 11, 2026Updated 2 months ago
- Native full-duplex speech dialogue inference for BayLing-Duplex.☆100Jun 22, 2026Updated 4 months ago
Are these results useful?