Rumble-2-Flash: Reson8's Open 0.5B Speech-to-Text Model
Reson8 released Rumble-2-Flash, an open 0.5B speech-to-text model for 40+ languages under Apache 2.0. How to run it, benchmarks, and what it leaves out.

Reson8 released Rumble-2-Flash, an open 0.5B speech-to-text model for 40+ languages under Apache 2.0. How to run it, benchmarks, and what it leaves out.

ElevenLabs extends 1 Million Voices from speech to song: people with permanent voice loss can get free ElevenMusic, with eligibility checked by SONA.

OpenAI will retire ChatGPT's Advanced and Standard voice on December 11, 2026. Live voice becomes the default; video and screen sharing stay on Advanced.

IK Multimedia's ReSing Choir turns one vocal take into up to five AI-modeled singers with chord-aware harmonies, offline, for a $149.99 intro price.

3CX V20 Update 10 lets ChatGPT or Claude query call data over MCP, adds Grok for AI agents, a backup route when the AI fails, and transcription on a Mac.

BARS, an ISMIR 2026 research model, raps your lyrics over your beat in a voice from a 3-second clip, with its own tempo control. Here is how it works.

Google added on-device speech recognition and text-to-speech to AI Edge Gallery, with ML Kit APIs for Android and open .litertlm voice models elsewhere.

Delhi lab Chariot launched a TTS model for 11 Indic languages and English, with code-mixing and voice cloning. Free to start; paid plans from ₹499 a month.

Fish Audio's Live 3 is a full-duplex voice model that listens while it speaks. It is English-only for now, with agents at $0.035 a minute until Dec 31.

Yamaha released VOCALOID7 on Nov 11, 2026: a second-generation VOCALOID:AI engine, Cubase Key Editor input, five new voicebanks, and a $129 editor.

ElevenLabs used its New York Summit to preview ElevenAI, agent Memory and Routines, custom fine-tuning, a partner marketplace and a bigger Nvidia deal.

Zyphra's ZONOS3-Mini is a small open voice-cloning model that runs in a browser. What you can control, how fast Zyphra says it is, and what it costs.

How ChatGPT Voice works: Live, Advanced and Standard options, starting a chat on phone or web, voices, screen sharing, and what happens to your audio.

AI accessibility tools as of November 2026: Be My AI, Seeing AI, Lookout, Live Caption, Immersive Reader, Read&Write, Speechify and Goblin Tools.

Gemini Live lets you talk with Gemini out loud and interrupt it. How to start a Live chat, share your camera or screen, use apps, and change settings.

Antigravity's new voice mode, built on Gemini Live, lets you give the agent tasks, steer its work and answer permission prompts out loud, in the app and CLI.

Gradium's Phonon is a family of small open text-to-speech models that run on your device. Which model to pick, licenses, benchmarks and how to try it.

CHIMERA is an MIT-licensed browser synth that speaks, sings and beatboxes from a simulated airway, not samples. An AI agent tunes it against real voices.

Underdog Woof is an English text-to-speech model of 31.7 MB or 40.6 MB that runs on a laptop CPU or in a browser, offline. Accuracy claims and license.

Prosecutors say three men allegedly used AI to mimic CEOs and big-firm lawyers and got staff to wire over $129 million. One defendant denies any role.
