
Best Open-Source TTS Models for Self-Hosting in 2026
The best open-source text-to-speech models in 2026 - covering Kokoro, Chatterbox, Fish Speech, Dia, Voxtral, and Piper with real hardware requirements and licensing details.
They summarize our coverage. We write it.
Newsletters like this one rebroadcast our headlines - often without the full review, the source reading, or the analysis underneath. Our weekly briefing sends the work they paraphrase, straight from the desk, before they get to it.
Free, weekly, no spam. One email every Tuesday. Unsubscribe anytime.

The best open-source text-to-speech models in 2026 - covering Kokoro, Chatterbox, Fish Speech, Dia, Voxtral, and Piper with real hardware requirements and licensing details.

Mira Murati's startup unveils TML-Interaction-Small, a 276B MoE model that hits 0.40-second response latency by listening and generating speech at the same time.

Vapi closes a $50M Series B at $500M valuation after Amazon Ring routed 100% of its inbound calls through the platform, chosen over 40 competing voice AI vendors.

OpenAI's second-generation real-time audio model with GPT-5-class reasoning, 128K context, five reasoning levels, and parallel tool calling - now generally available in the Realtime API.

OpenAI's Realtime API exits beta with GPT-Realtime-2, Translate, and Whisper - three specialized voice models splitting reasoning, translation, and transcription into distinct endpoints.

Apple's iOS 27 'Extensions' feature lets users swap Claude, Gemini, or ChatGPT into Siri, Writing Tools, and Image Playground - the first time rival AI models can power Apple Intelligence natively.

OpenAI published how they rearchitected their WebRTC stack to serve 900M weekly voice users on Kubernetes using a split relay and transceiver model.

Gemini arrives in 4 million GM vehicles and 16 Volvo models via OTA update as GM phases out Apple CarPlay by 2028. The in-car AI platform war is now a real fight.

A hands-on comparison of the top AI podcast creation tools in 2026 - covering recording, editing, voice cloning, and publishing for every budget.

Six AI language learning tools tested and compared by price, language coverage, speaking practice quality, and who each one actually suits.

A hands-on comparison of the top AI audio editing tools in 2026, covering noise removal, stem separation, mastering, and podcast production.

Hands-on comparison of Bland AI, Retell AI, Air AI, Vapi.ai, and Cal.com AI - five platforms for automated phone calls with verified pricing, latency numbers, and honest shortcomings.