2.0.2 · Speex

What's New

Speex: Multi-Vendor Speech Synthesis

A complete redesign of text-to-speech with support for multiple providers:

• Web Speech API - Zero-config browser-native voices (works offline)
• LocalAI - Self-hosted TTS with Kokoro, Bark, Piper backends
• ElevenLabs - High-quality voice synthesis and cloning
• OpenAI TTS - gpt-4o-mini-tts with voice instructions, plus tts-1 and tts-1-hd

Engines auto-detect from your configured LLM services—no duplicate API key entry. Priority-based fallback ensures speech always works.

Also New

• Claude Opus 4.5 full support
• Starred models for quick access
• Continued stability improvements

Full Changelog: https://github.com/enricoros/big-AGI/compare/v2.0.1...v2.0.2

Get Started

Available now at big-agi.com, via Docker, or self-host from source.