Users report Gemini 3.1 Flash TTS cutting out mid-generation; Google says next model in the works
AshishTheArtist · x · 2026-09-21
Artist and user AshishTheArtist publicly detailed issues with Gemini 3.1 Flash TTS via Google AI Studio: generated audio intermittently cuts in and out mid-generation, and sometimes entire passages fail to convert to speech at all. He said he had messaged several people connected to the project to help improve the next model.
Google's JJJDChoi replied that the team is "working hard on the next model," indirectly confirming a successor TTS is in progress. The thread serves as a real-world signal about the current model's stability.
More from Models
- ChatGPT now links to brand homepages far more, reshaping brand-mention tracking — lilyraynyc · 2026-11-12
- YC-backed Monte launches post-training platform to build proprietary models from your agents' real work — ycombinator · 2026-11-12
- Leak Claims OpenAI Will Launch Entire GPT-6.2 Family Tomorrow to Counter Opus 5.5 and Fable 5.2 — heypearlai · 2026-11-12
- ARC-AGI-3 leaderboard: models score 90%+ but at $10K+ per task — haider1 · 2026-11-12
- LMArena Launches Agent Arena for Head-to-Head Agent Evaluation — arena · 2026-11-12
- LLMs lack hyperlocal municipal data, explains disputed Texas power outage debate — csuwildcat · 2026-11-12