pickfit

BrowseLocal AI tools

Speechos

Local-first speech workspace to record, transcribe, analyze and synthesize speech on-device.

Use it

Before you install: known vulnerabilities

pickfit found 13 known high or critical vulnerabilities in the packages a fresh install brings (OSV.dev, 3 Nov 2026). Weigh this before you install it.

  • npm:next 16.4.0 Next.js: Unauthenticated Remote Code Execution in Image Optimization API when SVG files are used (GHSA-2464-fhr4-w9xw, critical, fixed in 16.4.1)
  • pypi:certifi 2026.7.22 certifi bundles emSign root CAs with compromised intermediate CA keys (GHSA-6q48-6c7w-9gw2, critical, fixed in 2026.10.18)
See 8 more

3 more findings not listed here.

Linux x86_64

You need first

  • Runtimes: Node.js 22+ and pnpm, Python 3.11-3.13 and uv
  • A GPU is optional
  • Keys or accounts: HF_TOKEN for pyannote diarization
  1. Install pnpm prerequisite via npm

    npm install -g pnpm
  2. Clone Speechos repo

    rm -rf speechos && git clone --depth 1 https://github.com/miikkij/Speechos speechos
  3. Install web via pnpm (candidate 1)

    cd speechos/web && pnpm install
  4. Install API lightweight CPU env via requirements-ci

    cd speechos/api && uv venv --python 3.12 && uv pip install -r requirements-ci.txt

Check that it works

pnpm --version

The output should contain “12.16.1”.

First thing to try

cd speechos/api && uv run --no-sync pytest -q

What it does

These come from the README; pickfit didn’t check them one by one.

  • Record or upload speech audio
    Not tested
  • Transcribe speech with speakers and emotion
    Not tested
  • Turn text into speech with different voices
    Not tested
  • Compare speech models side by side
    Not tested

How far pickfit got

Linux x86_64

  1. Installs
  2. Starts
  3. Answers requests
  4. Works offline

Windows and macOS: the project says it runs there; pickfit hasn’t tried it.

Good for

  • record microphone or upload audio file for transcription
  • analyze speech for transcript, emotion, speakers and voice features
  • synthesize text to speech with language voices and WAV download
  • export transcripts to TXT, SRT or JSON
  • choose local STT, TTS, emotion and speaker models per hardware tier

How pickfit tested it

Each run starts from a clean machine and follows the steps above. How pickfit verifies

Linux x86_64

Its service answers requests

  • Replayed from scratch
  • Works offline
  • Checked on 30 Oct 2026
  • Version 0.1.0

Differences the test machine hit

  • README: cd api && uv sync --extra gpu (omit on CPU-only machines)
    In the test: On this CPU-only 2 GB box used the CI lightweight env instead: `uv venv --python 3.12 && uv pip install -r requirements-ci.txt`; unit tests and /health run without torch via lazy model loading
  • README: Prereq Node.js 22+ and pnpm; cd web && pnpm install
    In the test: Ran `npm install -g pnpm` first; box had node 22/npm/uv but pnpm was missing

How to read a tool card

Stitching
pickfit installed this tool itself. Everything under the stitches comes from that run. A tool pickfit has not run never gets stitches.
Verified on your OS
The install steps ran on the system you chose. “Ran on Linux only” means it has not been run on yours yet.
macOS, Linux and WindowsWhere it ran
Green OS marks: pickfit ran the install steps there. Grey ones: the README says it runs there, and pickfit has not tried.
How far the run got
Installs and starts, its main function works, its service answers, it produces model output. A window means a desktop app opened; a plug, an MCP client used it. The mark sits beside the run’s result, under “Why it fits and how we know” and in “How pickfit tested it”.
Visual check
pickfit looked at screenshots of the app. Green: it looks right. Amber with a number: things that look wrong; open it to see them. Grey and dashed: not checked yet.
Known vulnerabilities
Known high or critical vulnerabilities (OSV.dev) in what it installs. Green: none known. Red with a number: how many; open it for the list, and read it before you install. Grey and dashed: not checked, which does not mean safe.
About the run
The day it ran, and the version that ran.
Source of a reason
Every reason a pick fits rests on one profile field. Open the reason to see the field and the value it relies on.
Hidden gem
High quality, little known.
Quality and popularity
Two scores out of 100. Quality: how well it installed and worked when pickfit tried it, and how good its install docs and upkeep are. Popularity: from stars, downloads and Hacker News.
Features checked
Of the main features the README advertises, how many the run actually exercised (green), and how many failed (red). Grey ones were not checked, and the card says why.
Not verified
A well-known tool Fitz mentions from general knowledge. No run record, no steps, no score.