Fish Audio's new voice model panned: full-duplex claims don't hold up, hype is paid
realmrfakename · x · 2026-11-11
Well-known voice-AI community member realmrfakename gave a negative assessment of Fish Audio's new model:
- The audio sounds pretty bad and doesn't live up to the "full duplex model" claim, showing all the usual issues of an ASR-LLM-TTS pipeline.
- Turn taking may be slightly better, but it doesn't truly "know when to shut up".
- He also criticized the company for relying heavily on paid promotion on Twitter to hype the launch, said Drama 3 wasn't great either, and is bearish on Fish overall.
Context: this is a third-party technical rebuttal to a viral clip billed as "100% AI" audio.
More from Models
- Interpretability study: Qwen3's 'say' and 'do' circuits are structurally disconnected, unlike OLMo — Sauers_ · 2026-11-11
- Developer Says He Stopped Testing Model Configs After Carbon Landed — cgarciae88 · 2026-11-11
- Google's AudioFM Foundation Model Tops Audio Benchmarks, Powers 2B Daily Predictions — umpedronosapato · 2026-11-11
- Unverified Rumor: GPT 6.2 Astra and Possibly 6.2 Sol Landing This Thursday — imjustnewatai · 2026-11-11
- Pelican SVG test: Fable 5.2 takes 25 min/$25 vs Gemini 4 Hydrogen's 5 minutes — FinanceYF5 · 2026-11-11
- Same task, 4 AI workflows: Fable 5.2 wins at $6/2min vs GPT-6 Astra's $93/23min — FinanceYF5 · 2026-11-11