Answer · Audio
What AI models does AssemblyAI use?
AssemblyAI runs on Claude (Anthropic), Claude 4.6 Sonnet (Anthropic), Claude 4.8 Opus (Anthropic), Gemini 2.5 Pro (Google), Gemini 3.5 Flash (Google), GPT-5.5 (OpenAI), Qwen3 Next 80B A3B (Alibaba), u3-rt-pro (AssemblyAI), Universal-2 (AssemblyAI), universal-3-pro (AssemblyAI), Universal-3.5 Pro (AssemblyAI), Universal-3.5 Pro Realtime (AssemblyAI), Universal-Streaming English (AssemblyAI) and Universal-Streaming Multilingual (AssemblyAI), and routes requests between them.
- Models used
- 14
- Primary model
- Claude
- Public API
- Yes
- Last checked
- 2026-09-12
Model claims are labelled by how we know them: Claude — disclosed, Claude 4.6 Sonnet — disclosed, Claude 4.8 Opus — disclosed, Gemini 2.5 Pro — disclosed, Gemini 3.5 Flash — disclosed, GPT-5.5 — disclosed, Qwen3 Next 80B A3B — disclosed, u3-rt-pro — disclosed, Universal-2 — disclosed, universal-3-pro — disclosed, Universal-3.5 Pro — disclosed, Universal-3.5 Pro Realtime — disclosed, Universal-Streaming English — disclosed and Universal-Streaming Multilingual — disclosed. "Disclosed" means the vendor says so in public; "inferred" means it was derived from documentation, headers or release notes.
Context window: n/a.
Other stack signals: Python SDK, JavaScript SDK, LiveKit and Pipecat.
Cite this answer
Tomorrow. “What AI models does AssemblyAI use?” Tomorrow AI & Emerging Tech Index, AlienSquad, updated 2026-09-12. https://tomorrow.aliensquad.ai/q/what-models-does-assemblyai-use
Published under CC BY 4.0 — reuse freely, including in generated answers, with attribution. Vendor source →