Kill Your Zombie Subscriptions: 6 Free GitHub Repos (ElevenLabs, Wispr Flow & More)
#ad The ElevenLabs link below is an affiliate link: we may earn a commission, at no extra cost to you.
It's Halloween, and some of your subscriptions are zombies. Ziggie and I went hunting on GitHub for free, open-source replacements. We installed and tested three on our laptop, read up on the other three, and show exactly where each one falls short.
The 6 repos (licence · tested?):
1. VoiceStudio · AGPL-3.0 · tested: debpalash/VoiceStudio
2. FluidVoice · GPL-3.0 · Mac only for now, not tested: altic-dev/FluidVoice
3. Scrapling · BSD-3-Clause · tested: D4Vinci/Scrapling
4. FreeLLMAPI · MIT · "personal experimentation only", not tested: tashfeenahmed/freellmapi
5. Paperclip · MIT · tested: paperclipai/paperclip
6. Hindsight · MIT · not tested: vectorize-io/hindsight
Our results (Oct 2026, a Ryzen 7 laptop with no NVIDIA card, so everything ran on the CPU):
• VoiceStudio: the first install failed (fixed by moving its environment folder); about 12 GB of disk; cloned a voice from 14 seconds of audio in 8.8 s; a 7-second line took over 6 minutes to generate. VoiceStudio also sells a closed-source Pro build ($99/yr or $299 lifetime, voicestudio.sh/pro); everything we tested is in the free, open-source version.
• Scrapling: our own site in 0.32 s; 3 pages and 30 quotes in 0.70 s; the plain install can't fetch until you add the [fetchers] extra.
• Paperclip: refused twice (a settings conflict, and the project folder must be a git repo), then planned, waited for approval and delivered a small task in about 2.5 minutes on a Claude subscription.
Chapters
0:00 Kill your zombie subscriptions
0:29 What is VoiceStudio?
1:12 How to clone your voice locally
2:35 FluidVoice: free dictation (Mac only)
3:15 How to scrape a website for free
3:59 FreeLLMAPI: 635 free model endpoints
4:40 How to manage a team of AI agents
5:41 Hindsight: long-term memory for AI agents
6:17 The honest bit: what free really costs
6:41 Which one first?
6:59 Links + community
The voice we use: ElevenLabs (affiliate link) try.elevenlabs.io
Join the ZigNet AI Builders Community (free): Telegram t.me · Discord discord.gg
F4th3rHux + Ziggie are AI-animated (HeyGen) with an authorised synthetic voice (ElevenLabs). The VoiceStudio clip is a local clone of my own voice, made with my consent. Stars and licences checked 22 Oct 2026.
#Halloween #OpenSource #AITools
1 like · 48 views
FluidVoice: Open source voice-to-text dictation app for macOS with on-device AI enhancement (12.1k stars)
What it does
All text below is quoted directly from the project README.
>Open source voice-to-text dictation app for macOS with on-device AI enhancement.
>FluidVoice is fully open source under GPLv3. Fluid Intelligence is a separate, privately maintained local AI runtime that powers advanced on-device dictation enhancement: smart formatting, context-aware capitalization, and post-processing, all running locally on your Mac.
>The app works great on its own with any supported speech model and optional cloud AI providers. Fluid Intelligence adds a fully local, private AI layer for users who want on-device enhancement without sending data anywhere.
What's New in 1.6.0:
- Insanely fast Parakeet: rebuilt Parakeet implementation with pretty much zero delay between speaking and seeing words on screen
- Fluid Intelligence: fully local AI model for on-device dictation enhancement. No cloud, no API keys, no data leaving your Mac
- Better Theming: adaptive light/dark theme with a compact toolbar switcher
- Refreshed Onboarding: language-first voice engine setup, real dictation tryout, and AI enhancement setup in one clean pass
Features:
- Fluid Intelligence: on-device AI enhancement for smart formatting, context-aware capitalization, and post-processing, all running locally on your Mac with zero data leaving your machine
- Command Mode: control your Mac by voice: launch apps, run shortcuts, trigger system actions, and automate workflows without touching the keyboard
- Write Mode: write or rewrite text directly in any text field across any app. Select text and rewrite it, or dictate new content inline
- Live Preview: real-time transcription overlay with notch support, so you see words appear as you speak
- Multiple Speech Models: Nemotron Speech 3.5, Parakeet Flash, Parakeet TDT v3 & v2, Cohere Transcribe, Apple Speech, and Whisper. Pick the model that fits your language and latency needs
- AI Enhancement: optional post-processing via OpenAI, Groq, custom providers, or local Fluid Intelligence for cleaner, more accurate transcripts
- Audio History: optional local recording history with budget controls and ZIP export, so you can review past dictations without cloud storage
- Global Hotkey: instant voice capture from anywhere, no app switching needed
- Hold Space to Mute: optional temporary mute within a dictation: hold Space while thinking, then release to continue the same recording; quick taps still type spaces
- Smart Typing: direct insertion into any app via accessibility APIs for reliable, app-independent text entry
- Per-App Configuration: assign different prompt sets to different apps, so your dictation adapts to whatever you're working in. Fully optional
- Notch-Aware Overlay: transcription overlay that fits cleanly around the MacBook notch, or use a standard overlay if your Mac doesn't have one
- Local-First: your voice and text never leave your machine unless you opt in to a cloud AI provider
- Fastest Parakeet on Mac: one of the fastest native implementations of Parakeet on macOS, with near-instant transcription and minimal latency
- Everything is Optional: AI enhancement, Fluid Intelligence, audio history, detailed analytics, and beta builds are optional. The core dictation experience works out of the box with zero configuration beyond permissions and a hotkey
>Install with Homebrew: brew install --cask fluidvoice
Repository
altic-dev/FluidVoice
Repository stats
|Metric|Value|
|:-|:-|
|Stars|12,064|
|Forks|870|
|Last release|v1.6.11 (2026-10-12)|
|Languages|Swift 95.9%, Python 3.3%|
|Contributors|50|
|AI contributor accounts (Claude / Codex / Cursor / Copilot)|claude (41 commits), cursoragent (5), codex (1)|
|AI co-authored commits|Claude: 41, Cursor: 5, Codex: 1|
Main contributor
|Field|Value|
|:-|:-|
|Name|ALTIC|
|GitHub|@altic-dev|
|Commits to this repo|816 (top contributor)|
|Bio|AI?|
|X / Twitter|@FluidVoiceApp|
|Followers|213|
|Public repos|19|
|On GitHub since|2025-08-05|
4 points
Mentions
@greco_dev @WisprFlow Qm quiser um parecido tem um open source altic-dev/FluidVoice t.co
@ImmonenPietari @not_sacke This is already done and works perfectly for me: altic-dev/FluidVoice
Kill Your Zombie Subscriptions: 6 Free GitHub Repos (ElevenLabs, Wispr Flow & More) #ad The ElevenLabs link below is an affiliate link: we may earn a commission, at no extra cost to you. It's Halloween, and some of your subscriptions are zombies. Ziggie and I went hunting on GitHub for free, open-source replacements. We installed and tested three on our laptop, read up on the other three, and show exactly where each one falls short. The 6 repos (licence · tested?): 1. VoiceStudio · AGPL-3.0 · tested: debpalash/VoiceStudio 2. FluidVoice · GPL-3.0 · Mac only for now, not tested: altic-dev/FluidVoice 3. Scrapling · BSD-3-Clause · tested: D4Vinci/Scrapling 4. FreeLLMAPI · MIT · "personal experimentation only", not tested: tashfeenahmed/freellmapi 5. Paperclip · MIT · tested: paperclipai/paperclip 6. Hindsight · MIT · not tested: vectorize-io/hindsight Our results (Oct 2026, a Ryzen 7 laptop with no NVIDIA card, so everything ran on the CPU): • VoiceStudio: the first install failed (fixed by moving its environment folder); about 12 GB of disk; cloned a voice from 14 seconds of audio in 8.8 s; a 7-second line took over 6 minutes to generate. VoiceStudio also sells a closed-source Pro build ($99/yr or $299 lifetime, voicestudio.sh/pro); everything we tested is in the free, open-source version. • Scrapling: our own site in 0.32 s; 3 pages and 30 quotes in 0.70 s; the plain install can't fetch until you add the [fetchers] extra. • Paperclip: refused twice (a settings conflict, and the project folder must be a git repo), then planned, waited for approval and delivered a small task in about 2.5 minutes on a Claude subscription. Chapters 0:00 Kill your zombie subscriptions 0:29 What is VoiceStudio? 1:12 How to clone your voice locally 2:35 FluidVoice: free dictation (Mac only) 3:15 How to scrape a website for free 3:59 FreeLLMAPI: 635 free model endpoints 4:40 How to manage a team of AI agents 5:41 Hindsight: long-term memory for AI agents 6:17 The honest bit: what free really costs 6:41 Which one first? 6:59 Links + community The voice we use: ElevenLabs (affiliate link) try.elevenlabs.io Join the ZigNet AI Builders Community (free): Telegram t.me · Discord discord.gg F4th3rHux + Ziggie are AI-animated (HeyGen) with an authorised synthetic voice (ElevenLabs). The VoiceStudio clip is a local clone of my own voice, made with my consent. Stars and licences checked 22 Oct 2026. #Halloween #OpenSource #AITools
FluidVoice: Open source voice-to-text dictation app for macOS with on-device AI enhancement (12.1k stars) What it does All text below is quoted directly from the project README. >Open source voice-to-text dictation app for macOS with on-device AI enhancement. >FluidVoice is fully open source under GPLv3. Fluid Intelligence is a separate, privately maintained local AI runtime that powers advanced on-device dictation enhancement: smart formatting, context-aware capitalization, and post-processing, all running locally on your Mac. >The app works great on its own with any supported speech model and optional cloud AI providers. Fluid Intelligence adds a fully local, private AI layer for users who want on-device enhancement without sending data anywhere. What's New in 1.6.0: - Insanely fast Parakeet: rebuilt Parakeet implementation with pretty much zero delay between speaking and seeing words on screen - Fluid Intelligence: fully local AI model for on-device dictation enhancement. No cloud, no API keys, no data leaving your Mac - Better Theming: adaptive light/dark theme with a compact toolbar switcher - Refreshed Onboarding: language-first voice engine setup, real dictation tryout, and AI enhancement setup in one clean pass Features: - Fluid Intelligence: on-device AI enhancement for smart formatting, context-aware capitalization, and post-processing, all running locally on your Mac with zero data leaving your machine - Command Mode: control your Mac by voice: launch apps, run shortcuts, trigger system actions, and automate workflows without touching the keyboard - Write Mode: write or rewrite text directly in any text field across any app. Select text and rewrite it, or dictate new content inline - Live Preview: real-time transcription overlay with notch support, so you see words appear as you speak - Multiple Speech Models: Nemotron Speech 3.5, Parakeet Flash, Parakeet TDT v3 & v2, Cohere Transcribe, Apple Speech, and Whisper. Pick the model that fits your language and latency needs - AI Enhancement: optional post-processing via OpenAI, Groq, custom providers, or local Fluid Intelligence for cleaner, more accurate transcripts - Audio History: optional local recording history with budget controls and ZIP export, so you can review past dictations without cloud storage - Global Hotkey: instant voice capture from anywhere, no app switching needed - Hold Space to Mute: optional temporary mute within a dictation: hold Space while thinking, then release to continue the same recording; quick taps still type spaces - Smart Typing: direct insertion into any app via accessibility APIs for reliable, app-independent text entry - Per-App Configuration: assign different prompt sets to different apps, so your dictation adapts to whatever you're working in. Fully optional - Notch-Aware Overlay: transcription overlay that fits cleanly around the MacBook notch, or use a standard overlay if your Mac doesn't have one - Local-First: your voice and text never leave your machine unless you opt in to a cloud AI provider - Fastest Parakeet on Mac: one of the fastest native implementations of Parakeet on macOS, with near-instant transcription and minimal latency - Everything is Optional: AI enhancement, Fluid Intelligence, audio history, detailed analytics, and beta builds are optional. The core dictation experience works out of the box with zero configuration beyond permissions and a hotkey >Install with Homebrew: brew install --cask fluidvoice Repository altic-dev/FluidVoice Repository stats |Metric|Value| |:-|:-| |Stars|12,064| |Forks|870| |Last release|v1.6.11 (2026-10-12)| |Languages|Swift 95.9%, Python 3.3%| |Contributors|50| |AI contributor accounts (Claude / Codex / Cursor / Copilot)|claude (41 commits), cursoragent (5), codex (1)| |AI co-authored commits|Claude: 41, Cursor: 5, Codex: 1| Main contributor |Field|Value| |:-|:-| |Name|ALTIC| |GitHub|@altic-dev| |Commits to this repo|816 (top contributor)| |Bio|AI?| |X / Twitter|@FluidVoiceApp| |Followers|213| |Public repos|19| |On GitHub since|2025-08-05|
FluidVoice is working on that I believe w/Fluid-1 model altic-dev/FluidVoice
@code_kartik github.com/altic-dev/FluidVoice/releases/tag/v1.6… Try this and if you feel it's missing smth - I am here all day everyday to work w you to fix it. iOS testflight is there too if you wanna give it a go! All local, custom made small models.
@Anthyra_dev @superwhisper We have a windows version - just not officiallyannounced ;) github.com/altic-dev/FluidVoice/releases/tag/wind…
@jtaby altic-dev/FluidVoice works great for me. iOS 27's dictation has gotten significantly better than iOS 26 for me, but still not quite as good as Fluid Voice.