Back to browse
PocketTTS-raven – fast local in-browser TTS with voice cloning

PocketTTS-raven – fast local in-browser TTS with voice cloning

by pantelisk·Jul 8, 2026·4 points·4 comments

AI Analysis

●●●BangerWizardryZero to One

Voice cloning in your browser with WASM — audio never leaves your machine.

Strengths
  • Native C++ and WASM builds enable CPU-only inference without GPU
  • Sub-400ms latency optimized for realtime conversational AI systems
  • Cloned voices stay on-device with no cloud API calls
Weaknesses
  • 67 MB model download on first load may deter some users
  • Voice cloning requires 6-12 seconds of clean audio input
Category
Target Audience

Developers building local-first AI applications

Similar To

ElevenLabs · PlayHT · Coqui TTS

Similar Projects

AI/ML●●Solid

KokoClone – Zero-shot voice cloning using Kokoro TTS

Kokoro voice cloning with multilingual support, but voice cloning itself is crowded.

Niche GemShip It
Ashish106
214mo ago
AI/ML●●Solid

Local Voice Assistant

Qwen3-TTS voice cloning without finetuning in ~1 second on RTX 5070.

WizardryCozy
armcat
204mo ago
AI/ML●●Solid

My 16MB vibe-coded voice cloning app

Shrinks the usual TTS bloat into a 16MB Electron-alternative wrapper while still letting you clone voices from a short sample and 'design' voices from text prompts. It handles model downloads for you, supports batch exports and macOS auto-updates — smart product trade-offs. Caveat: the app binary is tiny, but the underlying TTS models are downloaded on demand, so expect large model pulls behind the scenes.

Dark HorseWizardryShip It
yoav
204mo ago
AI/ML●●●Banger

I built a free CharacterAI that runs locally

Free local CharacterAI with voice cloning under 10s audio, plus ESP32 hardware integration.

Zero to OneWizardrySolve My Problem
akadeb
843mo ago
Hardware●●●Banger

An Open-Source Yoto Toy with Qwen3-TTS

Voice cloning on ESP32 without cloud beats Yoto's subscription model completely.

WizardryZero to OneDark Horse
akadeb
313mo ago