Multimodal model

OpenRouter Speech to Text

OpenRouter STT is OpenRouter’s unified speech-to-text interface for accessing transcription models through one API format. It standardizes audio transcription workflows across providers, enabling streaming and file-based speech recognition inside multimodal applications and realtime voice systems.

Type
Multimodal
Weights
Closed

More from OpenRouter

3

About OpenRouter

1

OpenRouter is a unified API platform giving developers and enterprises access to 400+ large language models from 60+ providers — including OpenAI, Anthropic, Google, and Mistral — through a single OpenAI-compatible endpoint. Features automatic failover, cost optimization, real-time billing, edge infrastructure, and org-wide data policies. Serves 5M+ users across 250k+ apps. Founded 2023 by Alex Atallah and Louis Vichy. Backed by a16z, Menlo Ventures, and Sequoia Capital.