Features

Core Features

Feature	Description	Guide
Voice	Real-time voice conversations with AI	Voice Guide
Chat	Text-based AI conversations	Chat Guide
Text-to-Speech	Generate natural speech from text	TTS Guide
Studio	Manage long-form TTS projects and exports	Studio Guide
Transcription	Convert audio to text	Transcription Guide
Diarization	Identify multiple speakers	Diarization Guide
Voice Cloning	Clone voices from audio samples	Voice Cloning Guide
Voice Design	Create voices from descriptions	Voice Design Guide

Feature	Web UI	Desktop	CLI	API
Voice	✓	✓	—	✓
Chat	✓	✓	✓	✓
Text-to-Speech	✓	✓	✓	✓
Studio	✓	✓	—	✓
Transcription	✓	✓	✓	✓
Diarization	✓	✓	—	✓
Voice Cloning	✓	✓	✓	✓
Voice Design	✓	✓	✓	✓

Start the server:

izwi serve

Open the web UI:

http://localhost:8080

Download required models:

izwi pull Qwen3-TTS-12Hz-0.6B-Base izwi pull Qwen3-ASR-0.6B-GGUF izwi pull Qwen3-8B-GGUF

Different features require different models:

Feature	Required Models
Voice	TTS + ASR + Chat model (or unified `LFM2.5-Audio-1.5B-GGUF`)
Chat	Chat model (Qwen3, Qwen3.5, LFM2.5, or Gemma)
Text-to-Speech	TTS model
Studio	TTS model
Transcription	ASR model (`Parakeet-TDT-0.6B-v3` default; Qwen3/Whisper/LFM2.5 also supported)
Diarization	`diar_streaming_sortformer_4spk-v2.1` (+ optional ASR and aligner models)
Forced Alignment	`Qwen3-ForcedAligner-0.6B` (or `-4bit`)
Voice Cloning	Qwen3 TTS Base model (`Qwen3-TTS-12Hz--Base`)
Voice Design	Qwen3 TTS VoiceDesign model (`Qwen3-TTS-12Hz-1.7B-VoiceDesign*`)

Choose a feature to learn more: