Skip to main content
Hopper serves open-source models for real-time voice agents: Google’s Gemma 4 31B for chat completions, k2-fsa’s OmniVoice for text to speech, and NVIDIA’s Nemotron ASR for speech to text. All three run behind one OpenAI-compatible API at https://api.withhopper.com/v1.

LLM

Chat completions on gemma-4-31b: streaming, tool calling, 25,000-token context.

Text to Speech

24 kHz streaming audio from omnivoice, with instant and pro voice cloning.

Speech to Text

Batch and streaming transcription on nemotron-asr: word timestamps, keyterm biasing, turn detection.

Quickstart

Get a key, make a request, stream a response.

Models

The catalog: model IDs, context windows, sample rates, pricing.

API Reference

Endpoint-level reference: auth, parameters, error shapes.