Speechos
Local-first speech workspace to record, transcribe, analyze and synthesize speech on-device.
Tested on LinuxKnown vulnerabilities
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 16.4.0Next.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 2026.7.22certifi bundles emSign root CAs with compromised intermediate CA keys (GHSA-6q48-6c7w-9gw2, critical, fixed in 2026.10.18)
See 8 more
npm:next 16.4.0— GHSA-673q-mjm6-r5xr (critical), fixed in 16.4.1npm:next 16.4.0— GHSA-p3m5-59mp-jv5r (high), fixed in 16.4.1npm:source-map-js 1.2.1— GHSA-68fv-2mgg-jv7q (high), fixed in 1.2.2pypi:filelock 4.0.12— GHSA-v4x8-3wr5-3wq8 (high), fixed in 4.2.1pypi:hydra-core 1.3.7— GHSA-wf6j-7hvr-gr93 (high), fixed in 1.3.8pypi:setuptools 74.1.3— GHSA-5rjg-fvgr-3xxf (high), fixed in 78.1.1pypi:transformers 4.57.6— GHSA-29pf-2h5f-8g72 (high), fixed in 5.3.0pypi:transformers 4.57.6— GHSA-fgcw-684q-jj6r (high), fixed in 5.5.0
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
Install pnpm prerequisite via npm
npm install -g pnpmClone Speechos repo
rm -rf speechos && git clone --depth 1 https://github.com/miikkij/Speechos speechosInstall web via pnpm (candidate 1)
cd speechos/web && pnpm installInstall 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 --versionThe output should contain “12.16.1”.
First thing to try
cd speechos/api && uv run --no-sync pytest -qWhat it does
These come from the README; pickfit didn’t check them one by one.
- Record or upload speech audioNot tested
- Transcribe speech with speakers and emotionNot tested
- Turn text into speech with different voicesNot tested
- Compare speech models side by sideNot tested
How far pickfit got
Linux x86_64
- Installs
- Starts
- Answers requests
- 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