Smallest AI's full voice stack hits 26.8% completion at $0.048/call on 300 hard calls
auto_grad_ · x · 2026-10-20
New on the VAmoS pareto frontier: @joshmeyer ran Smallest AI's complete voice stack (STT + LLM + TTS) against 300 realistic, difficult calls. TLDR: 26.8% task completion at $0.048 per call, placing it on the cost/completion frontier and pushing Hugging Face's stack off it. Smallest AI's own account amplified the result, so treat the vendor-adjacent benchmark with caution until independently verified.
More from Models
- Dream-1 robot control model claims 16x cheaper, 1.7x faster than LLM-based best — gharik · 2026-10-20
- Speculative decoding speeds up dense models more than MoEs, as intuition suggests — mervenoyann · 2026-10-20
- New decision model basal-omni-1.0-ultra claims near-frontier intelligence at much lower cost — tristanbob · 2026-10-20
- Inception Labs launches Mercury 3, a diffusion LLM claiming 1000 tok/s inference — cmrdporcupine · 2026-10-20
- Reasoning models can steer their chain of thought far better than earlier tests suggested, paper finds — dair_ai · 2026-10-20
- Same sources, same question: how Claude, NotebookLM and ChatGPT differ on one knowledge base — kbavandi · 2026-10-20