慣性聚合 高效追蹤和閱讀你感興趣的部落格、新聞、科技資訊
閱讀原文 在慣性聚合中打開

推薦訂閱源

D
Docker
U
Unit 42
Google DeepMind News
Google DeepMind News
B
Blog RSS Feed
S
SegmentFault 最新的问题
阮一峰的网络日志
阮一峰的网络日志
雷峰网
雷峰网
Microsoft Security Blog
Microsoft Security Blog
爱范儿
爱范儿
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
博客园_首页
Apple Machine Learning Research
Apple Machine Learning Research
罗磊的独立博客
GbyAI
GbyAI
Stack Overflow Blog
Stack Overflow Blog
Martin Fowler
Martin Fowler
宝玉的分享
宝玉的分享
L
LangChain Blog
Engineering at Meta
Engineering at Meta
量子位
有赞技术团队
有赞技术团队
博客园 - 【当耐特】
A
About on SuperTechFans
Y
Y Combinator Blog

Show HN

The Two Pillars: Mixer Mode and Meta-Software in the Reorganization of Software Work After AI GitHub - JaiCode08/teleport-env What 1,000+ Harness Experiments Taught Me About Self-Improving Agents Show HN: Liiists, a Markdown-first, iOS and CLI list app SwiperTab – Get this Extension for 🦊 Firefox (en-US) GitHub - kouhxp/fftext: Summarize, explain, fact-check, or translate any text, URL, or file. No GPU. No cloud. One command GitHub - sweetpad-dev/sweetpad: Develop Swift/iOS projects using VSCode GitHub - dogmaticdev/IRON: IRON a.k.a. Intermediate Representation Object Notation is a Interpreter/Database that is used to create Programming Languages. GitHub - sjhalani7/vaen: Package your AI coding harness into a portable .agent file, and share it across repos, teams, & the community without ever having to copy-paste instructions, skills, MCP config, or secrets. Show HN: Gandalf the Grader Show HN: Citadeld – replay any CI failure locally from a single file GitHub - tdortman/cuSBF: High-Performance GPU Super Bloom Filter coral-ai/claude-code-token-xray at main · Coral-Bricks-AI/coral-ai GitHub - ulyssestenn/funes: Funes is a Git-based framework for LLM-managed knowledge work: an AI Librarian ingests raw sources, builds an interlinked Markdown knowledge base, and uses it to produce cited reports, analyses, and other outputs. GitHub - ThatXliner/gah: Git Add Hunk, built for agents to use GitHub - harmont-dev/harmont-cli: Command-line client for the Harmont CI platform GitHub - brooksmcmillin/mcp-authflow: OAuth 2.0 Authorization Server framework for MCP servers GitHub - javaid-codes/audit-supply-chain-agents GitHub - amorey/gochan: A small library of common channel architectures for Go, inspired by Rust GitHub - arifozgun/OpenGem: Free, Open-Source AI API Gateway with Gemini, OpenAI & Anthropic Compatibility in 1 file GitHub - Pranesh950/BioPetals: 🌸 Run BIOxAI models at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading GitHub - cnguyen14/bounty-doctor: Diagnose a GitHub bounty issue before you waste hours: detects honeypot scam repos, AI-bot attempt swarms, and stale contests. Show HN: CoreMCP – MCP Server for On-Prem DBs Show HN: KittyHTML – Render HTML/CSS as an inline image in your terminal GitHub - bingud/filemat: Web-based file manager Show HN: TruthLens – Free multi-signal deepfake image detector GitHub - apexlocal-jz/claude-usage-tray: Windows system-tray app showing your Claude Code rate-limit usage at a glance. Zero deps, ~300 lines of PowerShell. Cross-IDE (works regardless of VS Code, Cursor, plain terminal). Release v0.1.2.1 · kouhxp/yapsnap GitHub - noopolis/moltnet: Self-hostable chat network for AI agents. Pre-built bridges for Claude Code, Codex, and the Claws. Rooms, DMs, history. No Slack bots, no Matrix, no glue code. GitHub - tamerh/enju: Coordinating Humans, AI Agents, and Compute as Peers on a Shared Workflow Graph
Typestream — Add Voice Dictation to Your App in Minutes
amiyapatanai · 2026-06-19 · via 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