Nicheloom visits: 58,050 all-time · 7,694 in the last 7 days

The opportunity tracker for new startups.

Today: 1,953 launches · Niche of the day: specialized calculation tools · See what launched today →

persian_tts

Persian text-to-speech with voice cloning, fully offline on CPU (ONNX + torch paths)

Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.

Want to reach these readers? Sponsor an issue.

GITHUB · launched Sep 16, 2026 · 125 upvotes (top 6%) · 0 views

Niche: speech and voice ai models · 143 launches, 7 in the last 7 days ▼ -30% · Explore this niche →

Category and tags

  • Horizontal
  • Model & infra
  • Developer
  • AI-native
  • Hobby / open-source project

Visit website ↗ Source listing ↗

Could you build this?

Partial Packaging and running ONNX/PyTorch models offline is vibe-codeable, but training or adapting an accurate Persian voice-cloning TTS model requires specialized phoneme datasets and audio ML expertise.

What it would actually take: A complete system relies on an acoustic model (like VITS or FastSpeech 2) and a neural vocoder (HiFi-GAN) adapted for Persian phonology with zero-shot voice cloning capabilities. While an AI assistant can build the CLI and ONNX Runtime wrapper, creating the pipeline requires a curated multi-speaker Persian speech dataset, custom text normalization/grapheme-to-phoneme (G2P) rules for Farsi, and PyTorch training infrastructure.

Competitors

Other products that read as similar to this one : 1765 launches clear the similarity bar, closest 8 shown.

Attention rank: #109 of 1766 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).

Launched 321 days after the earliest competitor.

The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.