Launched this week

Vois

Launched this week

Studio-quality text-to-speech and voice cloning, fully local

109 followers

Studio-quality text-to-speech and voice cloning, fully local

109 followers

Visit website

Podcasting Tools

•

Writing assistants

•

Text-to-Speech Software

Vois is a desktop voice studio for turning scripts, ebooks, articles, and podcasts into natural audio with 63 voices, voice cloning, and pro editing — no uploads, no per-character fees, no usage caps. Cloud voice tools charge per character, cap usage, and upload your scripts. Vois gives you studio-quality speech, voice cloning, and editing fully on your laptop or desktop.

Free Options

Launch tags:Productivity•Developer Tools•Artificial Intelligence

Launch Team / Built With

Tines — Build agents & automations integrated across your workspace

Build agents & automations integrated across your workspace

Promoted

Vois

Maker

📌

Hey Product Hunt! 👋 I'm Praney, and I built Vois as a solo maker over the past year. The backstory is personal. I'm partially dyslexic — long text has always been a struggle for me. Since high school, I've been converting articles, reports, academic papers, and white papers to audio so I could actually absorb them. I built a tool for myself that did exactly that. When I showed it to others, something unexpected happened. A friend wanted it for creating custom bedtime stories for her kids. Another had a stack of ebooks he'd bought but never read — he wanted to convert them to audio for his commute. Others, like me, had ADHD or dyslexia and immediately got it. That personal tool evolved into Vois — a full desktop voice AI studio. I also always wanted to create my own podcast but never felt my voice was good enough and didn't want to deal with the complexity of editing. Vois gives me that out of the box. What it does: → 63 studio-quality voices across 15 character archetypes → 3 TTS engines (fast drafts, expressive English, 23-language multilingual) → Voice cloning from a short audio sample → Script editor with multi-speaker dialogue → Multi-track timeline for mixing and arranging → Professional mastering (LUFS normalization, de-esser, EQ, limiter) → Smart caching — edit one sentence, only that chunk regenerates → Export to WAV, MP3, FLAC, AAC Everything runs on your machine. Nothing gets uploaded. No per-character costs. No usage limits. And unlike cloud services, you don't pay credits just to hear how a change sounds — Vois caches everything, so iterations are instant. The tech: Native Rust backend. No Python, no Docker. The fast engine generates at 6x real-time on Apple Silicon. Pricing: $29/month or $9/month on the annual plan. Free tier gives you 10 generations per day with full access to all voices and engines — no feature gating. 🚀 Launch offer for Product Hunt: 40% off the annual plan — $65/year ($5.40/mo). Code: PRODUCTHUNT. Valid until March 9. → https://vois.so/checkout?plan=ye... I'd love to hear how you'd use something like this — whether it's accessibility, content creation, game dialogue, or something I haven't thought of yet. I'll be here all day answering every question. 🙏 — Praney

Report

4d ago

@praney_behl Hi Praney. Congrats on the launch. What datasets were used to train the voice models?

Report

1d ago

Vois

Maker

@kimberly_ross Thanks! Great question. The TTS engines use models trained on publicly available speech datasets commonly used in speech synthesis research, clean, studio-quality speech corpora.

The 63+ production voices in the library were created using voice design techniques (generating voice characteristics from text descriptions) - they're not clones of real people.

For the voice cloning feature, the app requires users to confirm they have the voice owner's explicit consent before processing.

Happy to go deeper on any of this!

Report

1d ago

Sounds amazing, this could tie into my voice server for claude code.

One question, does it support African voices and intonations? Big gap here industry-wide.

Report

1d ago

Vois

Maker

@clement_ozemoya Absolutely, we are launching agent skill and accompanying vois-cli for programatic access soon.

Report

1d ago

The no uploads angle is the one that would actually sell me — I never loved the idea of sending scripts to a cloud service just to get audio back. How does the voice quality hold up on longer form content like a full chapter of an ebook? That's usually where these tools start to sound robotic.

Report

14h ago

Super! Your back story is inspiring, and congrats on the launch. Will give it a shot and let you know my feedback :)

Report

1d ago

Vois

Maker

@abhinavramesh Thanks Abhinav, I look forward to it. I hope you enjoy trying the app as much as I enjoyed building it.

Report

1d ago

Forum Threads

p/vois

•

2d ago

Text-to-audio for accessibility — where are the gaps?

I'm partially dyslexic. Long text has always been difficult for me not impossible, just slow enough that by the time I reach the bottom of a page, the top has faded. Since high school, I've been converting articles, papers, and reports to audio so I could actually absorb them.

Over the years I've tried everything: screen readers (functional but robotic), browser extensions (limited), cloud TTS services (good quality but expensive for heavy use), and various read-aloud apps.

None of them were quite right. Most are designed for occasional use read this one article, listen to this one page. They're not built for someone who processes a significant chunk of their reading through audio every single day.

The gaps I've personally experienced:

p/vois

•

2d ago

Launching Vois on Thursday 5th March — a desktop voice AI studio

Hey PH community,

I'm launching Vois on Thursday it's a desktop voice AI studio I've been building as a solo maker for the past year.

Some of you may have seen my earlier threads here about voice production costs for game devs, podcast workflows, audiobook production, and accessibility. Those conversations directly shaped what I built.

p/vois

•

3d ago

Local-first AI vs cloud AI — which is winning for voice generation?

Most voice AI services ElevenLabs, PlayHT, Murf run in the cloud. You upload your text, they generate audio, you download it. Per-character pricing.

But there's a clear shift toward local-first AI happening across the board. Apple's MLX framework, Ollama for LLMs, Whisper.cpp for transcription. Models are getting small enough and hardware is getting fast enough that "run it on your own machine" is a real option.

For voice generation specifically, the tradeoffs are interesting:

Cloud advantages:

View all