AssemblyAI adds Qwen3.5 4B: 1.9x faster voice rewrite, 94% cost cut
AssemblyAI · x · 2026-08-26
AssemblyAI has launched Qwen3.5 4B on its LLM Gateway, optimized for voice rewrite tasks central to voice products like dictation cleanup, transcript rewriting, and live formatting.
- Performance: Averages 612ms on voice rewrite tasks, 1.9× faster than GPT-4.1.
- Cost: 94% lower cost per hour of audio processed compared to GPT-4.1.
- Use Case: Designed for production volumes requiring speed and cost-efficiency without needing a frontier model.
Available to test with free credits, no credit card required.
More from Infra
- Turso Adopts AgentID to Grant AI Agents Independent OIDC Identities — glcst · 2026-08-27
- Idea: Blockchain-based prompt credentialing for AI models — Dsphar · 2026-08-26
- Foresight CEO: Open Science Needs Independent Secure Compute Clusters — allisondman · 2026-08-26
- Qwen3.8-Flash Runs Locally: 125B Model on Just 75GB RAM — danielhanchen · 2026-08-26
- CoreWeave Powers Physical AI for Wayve, Decart, NEURA, and Nissan — wandb · 2026-08-26
- Connect Amazon Bedrock AgentCore to cross-account knowledge bases — AWS ML Blog · 2026-08-26