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

Martin Fowler
Martin Fowler
L
LINUX DO - 最新话题
P
Proofpoint News Feed
Cyberwarzone
Cyberwarzone
Know Your Adversary
Know Your Adversary
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
L
Lohrmann on Cybersecurity
D
Darknet – Hacking Tools, Hacker News & Cyber Security
Security Latest
Security Latest
T
The Exploit Database - CXSecurity.com
Exploit-DB.com RSS Feed
Exploit-DB.com RSS Feed
P
Privacy & Cybersecurity Law Blog
K
Kaspersky official blog
The Last Watchdog
The Last Watchdog
Webroot Blog
Webroot Blog
Scott Helme
Scott Helme
T
Threat Research - Cisco Blogs
C
Cyber Attacks, Cyber Crime and Cyber Security
WordPress大学
WordPress大学
L
LINUX DO - 热门话题
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
博客园 - Franky
V
Visual Studio Blog
O
OpenAI News
AI
AI
Hacker News: Ask HN
Hacker News: Ask HN
V2EX - 技术
V2EX - 技术
GbyAI
GbyAI
Recent Commits to openclaw:main
Recent Commits to openclaw:main
Simon Willison's Weblog
Simon Willison's Weblog
S
Schneier on Security
Spread Privacy
Spread Privacy
Y
Y Combinator Blog
I
InfoQ
H
Hackread – Cybersecurity News, Data Breaches, AI and More
T
Threatpost
C
Cybersecurity and Infrastructure Security Agency CISA
F
Fortinet All Blogs
C
CERT Recently Published Vulnerability Notes
T
The Blog of Author Tim Ferriss
C
Check Point Blog
Apple Machine Learning Research
Apple Machine Learning Research
有赞技术团队
有赞技术团队
人人都是产品经理
人人都是产品经理
N
News and Events Feed by Topic
Project Zero
Project Zero
小众软件
小众软件
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
B
Blog
G
Google Developers Blog

Hacker News

randoFont GitHub - onehorizonai/silo-terminal: A dark phosphor Apple Terminal profile inspired by the sealed systems and green-blue screens of Silo. Fading Maize | 2001 to 2026 Show HN: Onboard-CLI–a fast developer tool built in Go uses AST and LLM Show HN: Finterm.ai Finance CLI for Claude Code and Codex Show HN: Codex Explorer,一款用于 Codex CLI 的本地会话管理器 Pylon — full-stack framework for coding agents GitHub - Corgea/Sighthound: Corgea's rule-based SAST scanner Kastra | Execution Governance for AI Systems devthropology.com Embersent — Know Exactly Who Read Your Document GodUI — UI Collection for Modern Interfaces Show HN: Reverse-engineering web apps into agent tools GitHub - Kuberwastaken/subagentmaxxing: Drive OpenAI Codex & Cursor CLI coding agents as subagents with the same ergonomics as native Claude Code subagents (grok-4.5, composer-2.5, gpt-5.5). Uniform run/fanout CLI + Claude Code skill. Aside Today I’m launching papercrane-cli: a BI tool built for Claude Code | Papercrane Blog Strata - Guess the City from a 3D Map a dark terminal Blocks.ai | Connect your agent to the world. Noticky — Sticky Notes & Always-on-Top Windows for Mac Make the hard day easier for the people you love CASHFLOW — Debt Network Optimizer 0 A.D.: Empires Ascendant FormGrid - Create Delightful Forms & Surveys for Free Codapult — Everything Your SaaS Needs, Already Wired Together LaTeX Diff Viewer - GitHub Marketplace LinguaGuessr analog.watch Estimania — Daily Estimation Game I Replaced Whisper with Parakeet on a $55/Month CPU Server. Here Is What Actually Happened. HyperSwitcher – Mac App & Window Switcher CLERC-DATA/epee · Datasets at Hugging Face EvenKeel — your money coach BareMetalRT — Bare Metal AI Build a Second Brain That Actually Remembers Why It Changed Tokenstead - Find AI Models for Your Hardware Fideby - Standing by the people you trust, when you can rubber duck GitHub - forgedculture/legibility-field-kit GitHub - ronak-create/FableCut: Zero-dependency browser video editor that AI agents can drive — JSON timeline, MCP + REST, live-reloading UI GitHub - BuceaGeorgia/VIRENA: A minimal Vision-Language-Action model you can read: frozen CLIP + a tiny head on ManiSkill PickCube. Runs on a Mac, no GPU. Fehu - Apps on Google Play GitHub - fresswolf/Slopera: The browser for the slop era Release Kiyeovo 1.0.0 · Realman78/Kiyeovo Noema — AI Company Analysis GitHub - hamidi-dev/opentab: 📊 Browse your AI coding spend in the terminal — OpenCode, Claude Code, Codex & more GitHub - sgInnora/wc2026-prediction-ledger: Receipt-verified AI prediction ledger for World Cup 2026: pre-kickoff sha256-locked forecasts scored vs results, with calibration + market baselines. Live: goalpulse.io/open-data GitHub - michaelwrites67-ctrl/yogen: 予言 Yogen — a 500-agent AI swarm that debates your idea and predicts the outcome. Self-host free with your own Anthropic key. GitHub - teddytennant/wizard: Self-extending autonomous agent in one Rust binary. One-line install, any provider (OpenAI-compatible, Anthropic, xAI) or fully local via llama.cpp, live /evolve self-modification, MCP, messaging gateway, built-in bench arcaide.foo Show HN: Android Developer Verification Package blacklisted in Aurora Store OpenDescent: Private messaging for normal people GitHub - tarunlnmiit/autopilot-jobhunt: AI job agent: scans 130+ careers pages nightly, scores every role against your resume with an LLM (0–100), alerts you on Telegram, and drafts tailored cover letters + resumes. Free & open source. 18 Words - Daily Word Challenge The State of US Local Government Accessibility 2026 flow - Real-time network throughput dashboard for the terminal. - Terminal Trove Battle LLM Robots GitHub - robesris/ffvii-realtime: Speed up Final Fantasy VII (Rebirth / Remake / Revelation) Tactical Mode slow-motion so combat plays at real-time speed Agent Sessions - Local History for AI Coding Agents Scrutora — code, cloud & consent compliance in one platform SoulOS Tutorials GitHub - gaemi/agentic-fc: Open-source football management simulation played by AI agents through MCP and watched through a TUI console. GitHub - talalalrwas/ocr-grab: Flameshot clone that adds OCR. GitHub - JustVugg/colibri: Run GLM-5.2 (744B MoE) on a 25GB-RAM consumer machine — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦 GitHub - saifmukhtar/kinetic figment computer linear.gratis - Free Linear Client Feedback Forms GitHub - atelier-ws/atelier: Runtime for coding agents. Models are getting smarter, but a model is only as capable as the environment supporting it. Atelier is that environment. https://atelier.ws Atlas · Tomesphere | Tomesphere Codenames Generator GitHub - lyfeninja/lyfeninja_blkseal_python_sdk: Lightweight Python client for signing and verifying digital content using lyfe.ninja's BlkSeal product powered by BlkBolt™. Designed for zero dependencies, simple integration, and exact content verification. DateTimeMate OpenScreenShot — Full-page screenshot & annotation tool for Chrome 38-0 — Build Your Premier League Dream Team Cyrinx — data over sound, measured GitHub - BhaveshThapar/mcp-audit HN Work GitHub - Northwood-Systems/foreman: Self-hosted LLM gateway. Cost effective, deterministic, and fast. Secure and private by default. A Visualization Language for the AI Era GitHub - weirdGuy/kastor: Declarative language and toolchain for AI agents: define agents, tools and prompts in HCL, then compile to frameworks or manage them on hosted platforms with plan/apply semantics. Abralo - Run multiple Claude Code agents in one window GitHub - mehranzand/repofleet: RepoFleet is an issue-centered CLI tool for managing Git workflows across multiple repositories. Pug — Open Source Product Analytics Chiptune Radio — Aleph Void, LLC Free Mermaid Live Editor & Diagram Maker GitHub - hirasso/html-obfuscator: Obfuscate emails, phone numbers, and other sensitive data in PHP. Invisible to humans, hidden from bots until they interact. Davit — a native macOS UI for Apple containers GitHub - rowboatlabs/rowboat: Open-source AI coworker, with memory Yamanote.fun PostgreSQL on AWS: Size & Benchmark EC2 Instances GitHub - Rodiun/frugon: Free, local, open-source LLM cost analyzer — see where your LLM bill leaks, on your machine. WhimFiles - Find Any File in Seconds Agent Draw: An agent draws while you talk, built on TLDraw Neil the Seal GitHub - animesh-94/Onboard-CLI: An AST-powered, local-first CLI that visualizes complex system architectures and enforces architectural boundaries via instant Git hooks. ridealong — live London trains Clusy | Agent-Native Notebook for ML and Data Science snowscroll · Instagram, without the spiral. GitHub - vishal-dehurdle/state-harness: Runtime safety net for LLM agents. Detects token spirals, kills doomed tasks early, tells you exactly why. Rust core, Python SDK. pip install state-harness GitHub - DO-SAY-GO/freelang: I love freelang
GitHub - gladiaio/gladia-cli
jilijeanloui · 2026-07-09 · via Hacker News

gladia banner

Build Release License: MIT Go

Audio to text, from your terminal. gladia transcribes any audio file or URL with the Gladia speech-to-text API — 100+ languages, speaker diarization, and code switching, in one command.

It is built for terminals, shell scripts, and pipelines:

  • One commandgladia transcribe <file-or-url> and you have a transcript
  • 100+ languages — auto-detected, constrained to a shortlist, or switched per utterance
  • Speaker diarizationwho spoke when, with --diarize
  • Pipe-friendly outputtext, json, json-full, srt, or vtt to stdout
  • Files or URLs — transcribe a local recording or a remote link, no download step
  • Zero config — one API key, no project setup, works in CI

Start here: Install · Quick start · Commands · Language · Diarization

Install

# macOS & Linux
curl -fsSL https://github.com/gladiaio/gladia-cli/releases/latest/download/install.sh | sh

# Windows (PowerShell)
powershell -c "irm https://github.com/gladiaio/gladia-cli/releases/latest/download/install.ps1 | iex"

Other platforms and binaries: GitHub releases. Build from source with make build (→ ./gladia).

The installer offers to set up shell tab completion when run interactively. To skip the prompt (e.g. in CI), set GLADIA_NO_COMPLETION_PROMPT=1. See Shell completion to configure it manually.

Quick start

gladia auth set your_key                    # get one at app.gladia.io/account

gladia transcribe meeting.wav               # transcript to stdout
gladia transcribe podcast.mp3 -o srt        # subtitles instead
gladia transcribe call.wav --diarize        # label who spoke when
gladia languages                            # list supported language codes

Setup once: get an API key at app.gladia.io/account, then provide it any of these ways (checked in order):

export GLADIA_API_KEY=your_key   # 1. environment
gladia auth set your_key         # 2. saved to ~/.gladia (mode 0600)
gladia transcribe … --gladia-key your_key   # 3. per-command flag

Everyday examples

# Transcribe a local file or a remote URL — no download step
gladia transcribe meeting.wav
gladia transcribe https://example.com/audio.mp3 -o json

# Narrow language detection to a shortlist
gladia transcribe podcast.mp3 --language en,fr,de

# Mixed-language audio: re-detect on every utterance
gladia transcribe mixed.mp3 --code-switching --language en,fr

# Who spoke when, as subtitles
gladia transcribe call.wav --diarize -o srt

# Pick a model
gladia transcribe podcast.mp3 --model solaria-3 --language en

# Machine-readable output straight into a pipeline
gladia transcribe interview.mp3 -o json | jq '.transcription'

Commands

Command Description
transcribe <source> Transcribe an audio file or URL
auth set <key> Save API key to ~/.gladia
languages List supported ISO 639-1 codes
completion <shell> Generate shell tab completion (bash, zsh, fish, powershell)

Flags (transcribe)

Flag Default Description
-o, --output text Output: text, json, json-full, srt, vtt
--language Expected language(s), comma-separated (en or en,fr,de); narrows detection, does not enable code switching
--cs, --code-switching off Re-detect language on each utterance (mixed-language audio; solaria-1 only)
--diarize off Identify speakers in the transcript
--model STT model: solaria-1 or solaria-3. Solaria-3 accepts at most one --language (en, fr, de, es, or it) and does not support code switching.
-v, --verbose off Show progress while polling

Global flag (any command): --gladia-key — API key if not in the environment or ~/.gladia.

Language

Goal What to run
Auto-detect transcribe <source>
Constrain detection --language en,fr,de (no code switching)
Code switching --cs or --code-switching (+ optional --language hints)
  • --language limits which language(s) Gladia considers (en,fr,de is a hint list, not per-utterance switching).
  • --cs / --code-switching turns on per-utterance language detection. Add --language to restrict which languages may appear. Not available with solaria-3.
gladia languages   # list valid codes

Diarization

Use --diarize when you need who spoke when. Off by default.

  • Works with any output format; most useful with -o text, srt, or vtt.
  • Speaker labels are included in the output (e.g. Speaker 0: …).
gladia transcribe meeting.wav --diarize
gladia transcribe panel.mp3 --diarize -o srt

Shell completion

When you install via install.sh or install.ps1, the script asks whether to configure tab completion for your shell. You can also set it up manually — gladia completion --help lists every shell.

bash

Requires the bash-completion package (on macOS: brew install bash-completion@2).

# current session
source <(gladia completion bash)

# persistent (user directory)
mkdir -p ~/.local/share/bash-completion/completions
gladia completion bash > ~/.local/share/bash-completion/completions/gladia
zsh
mkdir -p ~/.zsh/completions
gladia completion zsh > ~/.zsh/completions/_gladia

# add to ~/.zshrc if not already present:
# fpath=(~/.zsh/completions $fpath)
# autoload -U compinit; compinit
fish
mkdir -p ~/.config/fish/completions
gladia completion fish > ~/.config/fish/completions/gladia.fish
PowerShell
gladia completion powershell | Out-File -Append -Encoding utf8 $PROFILE

Restart your shell after installing completions.

Develop

make build && make test && make dist

License

MIT © Gladia