Use your OpenAI commitments on Baseten open models. Learn more

Tianshu Cheng

Forward Deployed Engineer

Model performance

Cost-efficient, high-performance TTS with Qwen3-TTS

Ian Carrasco

1 other

Fast, cost-efficient Qwen3-TTS

Model performance

The fastest Whisper — with streaming and diarization

William Gao

Tianshu Cheng

4 others

Baseten powers the fastest, most accurate, and cost-efficient Whisper transcription on the market, with streaming and diarization.

Model performance

Generally Available: The fastest, most accurate and cost-efficient Whisper transcription

William Gao

Derrick Yang

William Gao

3 others

The fastest Whisper

News

Introducing Custom Servers: Deploy production-ready model servers from Docker images

Bola Malek

Tianshu Cheng

2 others

Custom servers

Explore Baseten today

Start deploying Talk to an engineer