惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

MyScale Blog
MyScale Blog
人人都是产品经理
人人都是产品经理
云风的 BLOG
云风的 BLOG
小众软件
小众软件
F
Fortinet All Blogs
爱范儿
爱范儿
WordPress大学
WordPress大学
N
Netflix TechBlog - Medium
Recent Announcements
Recent Announcements
Google DeepMind News
Google DeepMind News
C
Check Point Blog
博客园 - 聂微东
D
Docker
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
aimingoo的专栏
aimingoo的专栏
Vercel News
Vercel News
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
A
About on SuperTechFans
博客园 - 【当耐特】
Microsoft Azure Blog
Microsoft Azure Blog
B
Blog
宝玉的分享
宝玉的分享
Jina AI
Jina AI
H
Hackread – Cybersecurity News, Data Breaches, AI and More

Hacker News: Show HN

PurrrrrFocus: Pomodoro Timer App - App Store Workflow Engine — Multi-Step Orchestration for Bun RapidPhoto: Pro Photo Editor App - App Store GitHub - DheerG/swarms: Achieve extraordinary results with claude code across a variety of tasks SPICE simulation → oscilloscope → verification with Claude Code — Lucas Gerads Show HN: VCoding – A 5 MB native Windows IDE with no dynamic dependencies Show HN: LLMs don't hallucinate because they're bad at math, it's the format GitHub - Agent-FM/agentfm-core: AgentFM is a peer-to-peer network that turns everyday computers into a decentralized AI supercomputer. AgentFM lets you run massive AI workloads directly across a global mesh of idle CPUs and GPUs. Show HN: Tracking Top US Science Olympiad Alumni over Last 25 Years GitHub - Potarix/agent-hub: One place to talk to all your agents Show HN: Runtime security for AI agents(injection,tool abuse, data exfiltration) GitHub - dubeyKartikay/lazyspotify: Terminal Spotify client for macOS and Linux GitHub - the-banana-tool/king-louie: Easy to use GUI Personal AI Assistant. Win/Linux/Mac. Show HN I made my vacation rental bookable by AI agents–no Airbnb, 0% commission GitHub - basteez/jsf-autoreload: maven plugin to enable hot reload on jsf projects uvm32/hosts/host-gdbstub at main · ringtailsoftware/uvm32 GitHub - labsai/EDDI: Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 12+ LLM providers, MCP/A2A protocols, RAG, persistent memory, and enterprise compliance (EU AI Act, GDPR, HIPAA). Built on Quarkus. GitHub - glitchnsec/fortyone-oss: AI Executive Assistant Platform Quickstart | Alien GitHub - muxshed/shed: One stream in, or many. Every destination, simultaneously. No cloud middleman, no per-channel fees, no limits. GitHub - ocrbase-hq/ocrbase: 📄 PDF/IMG ->.MD/JSON Document OCR API for PaddleOCR and GLMOCR. Self-hostable. GitHub - impactjo/home-memory: MCP server that lets your AI assistant remember everything about your home. GitHub - Sets88/dbcls: DbCls is a powerful terminal database client that supports various databases GitHub - neptun2000/heor-agent-mcp GitHub - SeanFDZ/macmind: Single-layer transformer in HyperTalk for the classic Macintosh RollQuation: Math Puzzles - Apps on Google Play GitHub - dropbox/witchcraft Show HN: Agent-cache – Multi-tier LLM/tool/session caching for Valkey and Redis GitHub - opentalon/opentalon: OpenTalon is an open-source platform built from the ground up in Go as a robust alternative to OpenClaw LinkedIn™ 职位抓取工具 - Chrome 应用商店
whisperbridge live translation (LiveKit V0)
priyanshu-mi · 2026-06-19 · via Hacker News: Show HN

whisperbridge

Free beta

Speak your language. They hear theirs — in your own voice.

Real-time voice translation for two people who don't share a language. You each just talk normally and hear the other in your own tongue — and it still sounds like the real them, not a robot.

Opt-in, consented voice. Runs in any browser — nothing for them to install.

Already have an account? Sign in

How it works

Two people, two languages, one natural conversation.

1

Start a call and share the link with anyone, anywhere.

2

Each of you picks the language you speak.

3

Just talk — you hear them in your language, they hear you in theirs.

Your real voice

It clones the speaker's voice, so the translation still sounds like them — warm and human, unmistakably you.

Real-time

Natural back-and-forth with about a second of delay. A real conversation, not stop-and-start subtitles.

Any language, any device

12 languages, right in your browser — phone or laptop, nothing to install. Free while in beta.

Privacy & trust

Your voice stays yours.

Whose voice gets cloned?

Only your own. The app has you record your own voice and confirm it's yours before anything is created — it won't clone someone else. Prefer not to? Captions and a standard voice work just as well.

Is my voice stored? Can I delete it?

It powers your translated speech on your calls and is tied to your account. You can re-record it anytime — and when you delete your account, we delete your voice from our systems and request its removal from our voice provider.

Who can hear me?

Only the person on your call, live. The translated audio is generated on the fly and delivered just to them — we don't post, publish, or sell it.

Is my voice sold?

Never — we don't sell your voice. It's processed by our speech provider, Cartesia, only to generate your translations.

I'm building whisperbridge on my own. I made it because the people I care about don't all share my language — and most translation tools flatten everyone into the same robot voice. whisperbridge keeps your own voice. It's an early beta with rough edges; if you try it, I'd genuinely love to hear what worked and what didn't.

— Priyanshu, building whisperbridge solo

Ready to talk across languages?