# πŸŽ™οΈ Clone Any Voice for Free β€” This Local App Replaces ElevenLabs **URL:** \ **Category:** Tools & Scripts\ **Tags:** freebies, ai\ **Created:** [February 21, 2026, 10:23am UTC](https://onehack.st/t/clone-any-voice-for-free-this-local-app-replaces-elevenlabs/318699 "2026-02-21T10:23:44Z")\ **Posts on this page:** 5\ **Page:** 1
**Author:** ![Shayla](https://onehack.st/user_avatar/onehack.st/shayla/32/174870_2.png) [@Shayla](https://onehack.st/u/Shayla)\ **Post date:** [February 21, 2026, 10:23am UTC](https://onehack.st/t/clone-any-voice-for-free-this-local-app-replaces-elevenlabs/318699/1 "2026-02-21T10:23:45Z")
# πŸŽ™ 3 Seconds of Audio β†’ Perfect Voice Clone β€” Free Desktop App, No Subscription ![](https://raw.githubusercontent.com/jamiepine/voicebox/main/.github/assets/icon-dark.webp) _Think ElevenLabs but it runs on your laptop, costs nothing, and your voice data never touches the internet._ **Someone built a local ElevenLabs.** Record 3 seconds of anyone’s voice, and Voicebox creates a clone that speaks any text you feed it β€” natural emotion, real cadence, not robotic TTS garbage. > _ElevenLabs charges $22-99/month and keeps your voice data on their servers. A professional voice actor charges $250-500 per finished minute. Voicebox is one download and $0 forever._ * * * > **🧠 How It Works β€” The 60-Second Version** > > Think of it like a voice photocopier. You feed it a short audio clip of someone talking β€” 3 to 10 seconds is enough. The AI model (Qwen3-TTS by Alibaba, same class as the paid services) learns the voice’s fingerprint: tone, rhythm, accent, emotion. Then you type any text and it speaks it back _in that voice_. > > The model downloads once (~2-4GB). After that β€” no internet needed. Everything runs on your hardware. > > | What Happens | Where It Happens | > | --- | --- | > | Voice sample analyzed | Your machine | > | Voice profile created | Your machine | > | Speech generated | Your machine | > | Data sent to cloud | **Nowhere. Ever.** | > **⚑ What You Get β€” Not Just a TTS Toy** > > | Feature | Details | > | --- | --- | > | **Voice cloning** | 3-10 seconds of audio β†’ near-perfect clone | > | **DAW-style timeline** | Multi-track editor β€” drag clips, layer voices, mix conversations | > | **Multi-voice projects** | Build entire podcasts with different cloned voices | > | **Transcription** | Built-in Whisper β€” auto-transcribes your audio | > | **In-app recording** | Record voice samples directly, no external tools needed | > | **Model sizes** | 1.7B (better quality) or 0.6B (faster, lighter) | > | **Languages** | English, Chinese, and more coming | > > This isn’t a command-line script for nerds. It’s a full production app with a proper UI. > **πŸ’» Download & Setup β€” Pick Your OS** > > πŸ“₯ **Download:** [github.com/jamiepine/voicebox](https://github.com/jamiepine/voicebox) > > | Platform | GPU Requirement | Speed | > | --- | --- | --- | > | **macOS (M1/M2/M3/M4)** | None β€” native Metal acceleration via MLX | Near real-time, 4-5x faster | > | **Windows** | NVIDIA GPU (CUDA) | Fast with decent GPU | > | **Linux** | Coming soon | Blocked by build infra | > > **Step 1 β€”** Download the installer from the GitHub releases page. > > **Step 2 β€”** Launch β†’ it auto-downloads the Qwen3-TTS model on first run. > > **Step 3 β€”** Record or upload a voice sample (3+ seconds). > > **Step 4 β€”** Type your text β†’ hit generate β†’ done. > > ⚑ **Mac users win here** β€” Apple Silicon gets native Neural Engine acceleration. Generation is near real-time. > **πŸ’° What This Replaces** > > | Service | Cost | Your Data | > | --- | --- | --- | > | **ElevenLabs** | $22-99/month | Stored on their servers | > | **Professional voice actor** | $250-500/finished minute | N/A | > | **Play.ht / Murf** | $29-99/month | Cloud-processed | > | **Voicebox** | **$0 forever** | **Never leaves your machine** | * * * **⚑ Quick Hits** | Want | Do | | --- | --- | | πŸŽ™ Clone a voice | β†’ Upload 3-10 sec audio clip β†’ instant profile | | 🎧 Build a podcast | β†’ Create multiple voice profiles β†’ arrange on timeline | | πŸ”’ Keep voice data private | β†’ Already done β€” nothing ever leaves your laptop | | πŸ”„ Use offline | β†’ Model downloads once, works without internet forever | * * * _Your laptop is now a voice studio. Nobody asked permission and nobody’s charging rent._ ---
**Author:** ![DukeForever](https://onehack.st/user_avatar/onehack.st/dukeforever/32/38179_2.png) [@DukeForever](https://onehack.st/u/DukeForever)\ **Post date:** [February 21, 2026, 3:37pm UTC](https://onehack.st/t/clone-any-voice-for-free-this-local-app-replaces-elevenlabs/318699/2 "2026-02-21T15:37:53Z")
very slow generation only works with GPU possibly with 10+ VRAM !! ---
**Author:** ![KOUSTHUBH\_lanka](https://onehack.st/user_avatar/onehack.st/kousthubh_lanka/32/155333_2.png) [@KOUSTHUBH\_lanka](https://onehack.st/u/KOUSTHUBH_lanka)\ **Post date:** [February 21, 2026, 3:43pm UTC](https://onehack.st/t/clone-any-voice-for-free-this-local-app-replaces-elevenlabs/318699/3 "2026-02-21T15:43:24Z")
yea very slow , its taking too long to download the qwen model while generating ---
**Author:** ![Thesharingmaster](https://onehack.st/user_avatar/onehack.st/thesharingmaster/32/154335_2.png) [@Thesharingmaster](https://onehack.st/u/Thesharingmaster)\ **Post date:** [February 21, 2026, 3:45pm UTC](https://onehack.st/t/clone-any-voice-for-free-this-local-app-replaces-elevenlabs/318699/4 "2026-02-21T15:45:55Z")
Only works reasonably on a 4090 or 5090. Luckily, I have both!! ---
**Author:** ![Asher](https://onehack.st/user_avatar/onehack.st/asher/32/119317_2.png) [@Asher](https://onehack.st/u/Asher)\ **Post date:** [February 21, 2026, 4:49pm UTC](https://onehack.st/t/clone-any-voice-for-free-this-local-app-replaces-elevenlabs/318699/5 "2026-02-21T16:49:43Z")
I’ve been trying the recently released MioTTS. It’s better, faster, runs on much lower VRAM, and only needs 5 seconds of audio recording to clone someone’s voice.