Hopper

Hopper is a realtime inference API for open-source models: two LLMs, text-to-speech and speech-to-text, behind a standard chat-completions API. Try the latest open-source models on your own work: in a chat, Hopper runs your prompt or examples on both LLMs side by side and returns each answer with time to first token, tokens per second, token counts and cost, so you can judge the models on your task. It also speaks text with an inline audio player, transcribes recordings you attach (WAV, MP3, M4A, Ogg, FLAC or WebM) with word timestamps, lists models and prices, and returns tested client code for popular SDKs and agent frameworks. After you sign in with your Hopper account, it shows your usage and creates API keys: the key opens once in the Hopper console, with a ready snippet for your code. Where it can run commands in your project, the plugin also finds the prompts your app sends and tests them on both models, and after you say go it points your project's chat-completions client at a Hopper model, changing only the client. Text and audio you send go to Hopper's API; see withhopper.com/privacy.