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

J
Java Code Geeks
Hugging Face - Blog
Hugging Face - Blog
博客园_首页
爱范儿
爱范儿
罗磊的独立博客
美团技术团队
Jina AI
Jina AI
量子位
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
酷 壳 – CoolShell
酷 壳 – CoolShell
有赞技术团队
有赞技术团队
V
V2EX
阮一峰的网络日志
阮一峰的网络日志
小众软件
小众软件
IT之家
IT之家
雷峰网
雷峰网
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
博客园 - 司徒正美
大猫的无限游戏
大猫的无限游戏
博客园 - 聂微东
月光博客
月光博客
人人都是产品经理
人人都是产品经理
博客园 - 三生石上(FineUI控件)

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
Typestream — Add Voice Dictation to Your App in Minutes
amiyapatanai · 2026-06-19 · via Hacker News: Show HN

Pay-as-you-go · No subscriptions

Give your users fast, highly accurate speech-to-text with just a few lines of code. Typestream is the developer-first API that’s incredibly easy to integrate and priced purely pay-as-you-go.

Why voice

More than a feature - a growth lever

Adding speech-to-text isn't just a nice-to-have. It changes how users adopt, trust, and stick with your product.

Up to 3× faster input

Drive Higher App Retention

Typing is the biggest point of friction in mobile and SaaS workflows. By letting users speak, you speed up data entry, search, and form submissions by up to 3x. Removing this friction directly correlates to higher task completion rates and long-term user retention.

Inclusive by default

Broaden Your Addressable Market

Typing isn't accessible or convenient for everyone. Adding reliable speech-to-text instantly makes your application inclusive for users with physical limitations, cognitive disabilities, or those working in "hands-busy" environments.

AI-ready input layer

Unlock Advanced Product Features

Voice is the ultimate input layer for modern software. By turning unstructured speech into highly accurate text, you empower your users to interact with AI assistants, generate automated summaries, or execute complex commands natively within your app.

Ephemeral by design

Build Trust Through Privacy

Users hesitate to adopt voice features if they fear their data is being stored or mined. Typestream processes audio ephemerally—delivering the text and immediately purging the data. You offer a premium experience while guaranteeing absolute privacy.

Built for developers

Professional UI Components

Mintlify-grade aesthetics with fluid animations for recording, processing, and success states. Completely SSR-compatible.

API First

Create, name, and revoke API keys from your dashboard. Secure by default, simple by design.

Multi-Language Support

  • Frontend: React, Next.js, Vanilla JS
  • Backend: Python, Go, Ruby, cURL
  • Agentic/AI: OpenAPI, MCP Server, skills.md

AI-agent ready

One prompt. Your agent does the rest.

Paste this into Cursor, Claude Code, or any coding agent. It will read typestream.dev/skills.md and wire voice dictation into your app. You only need to add your API key.

  1. Copy the prompt below
  2. Paste it into your agent
  3. Provide your API key when asked

Prompt

Add voice dictation to my app using Typestream. Follow the integration guide at https://typestream.dev/skills.md. Ask me for my Typestream API key and wire everything up — the key is the only thing you need from me.

Stop paying for what you don't use

No monthly fees. Buy credits, use them whenever.

1 Credit = 1 Minute of Audio

Starter Pack

$5

500 credits

Best Value

Pro Pack

$10

1,250 credits

Scale Pack

$20

3,000 credits

Securely powered by Stripe. One-click top-ups.

Built on Typestream

Typestream Voice for Chrome

A lightning-fast, privacy-first, open-source Chrome extension for AI speech-to-text dictation in every tab. Bring your own Typestream API key and pay only for what you use—no $15/month subscription.

Talk-then-send

Press a hotkey, speak, and release. Text is cleaned up and inserted exactly where your cursor is.

Absolute privacy

Your API key stays on your device. Typestream processes audio ephemerally with zero data retention.

Smart clipboard fallback

Dictating while reading another tab? Your transcript is copied to the clipboard when there is no active text field.

Open source

MIT-licensed and fully inspectable. Build from source today while we finish the Chrome Web Store listing.

Ready to give your app a voice?

Sign up in seconds and start building.

Get Started Now