Izwi: A Local-First Voice AI Runtime for Transcription and Cloning
tom_doerr · x · 2026-08-12
Izwi is a local-first voice AI runtime project. It supports real-time speech transcription, speaker diarization, text-to-speech (TTS), and voice cloning.
The project offers a desktop app, web UI, CLI, and local inference server. It exposes an OpenAI-compatible API, allowing developers to integrate and use it without relying on cloud services or API keys.
More from coding & agent
- Sequoia Shares Harvey's Playbook: Building Research-Level Legal Agents on a Budget — Scobleizer · 2026-08-12
- MiniMax H3 Video Generation Workflow: Prompt Rewriting Based on Reference Images — Askdevin777 · 2026-08-12
- DSRs, a DSPy Spin-off, Crosses 300 Stars; Dev Shares Architectural Evolution Thoughts — krypticmouse · 2026-08-12
- NVIDIA's 30B MoE Model Lands on Perplexity Agent API — denisyarats · 2026-08-12
- Kandev: A Self-Hostable AI Kanban Dev Environment for Multi-Agent Orchestration — tom_doerr · 2026-08-12
- The Flaw in AI Coding: Agents Execute Commands but Lack Product Logic Pushback — DavidKPiano · 2026-08-12