Gradium

@gradiumai

The voice layer for agents. Real-time, accurate, natural voice APIs: TTS, STT, turn-taking & voice design. Devs: build → https://gradium.ai

A user calls the suite state of the art in voice AI.

6 Sources, 8h ago, updated 8h ago

Gradium says teams already running inference on Baseten can deploy its TTS model with one click.

1 Source, 7d ago, first seen 7d ago

Gradium says the model's median time to first audio is under 100 milliseconds, down from 236 milliseconds for its previous model.

4 Sources, 14d ago, updated 14d ago

Gradium says the model scores highest for naturalness among sub-100ms models on Speko's public benchmarks.

2 Sources, 20d ago, first seen 20d ago

Gradium says users can describe a voice, generate it in seconds and use it directly in text-to-speech.

1 Source, 36d ago, first seen 36d ago

Featured in