Deepgram optimizes voice AI models at scale on AWS Trainium chips
1,400 organizations
Voice AI provider scales to quadrillions of audio tokens yearly on Trainium for 1,400+ organizations
Deepgram, which builds speech-to-text, text-to-speech, and voice agent models, moved its workloads to AWS Trainium to run its voice AI at scale. The company now handles quadrillions of audio tokens a year for more than 200,000 developers and 1,400 organizations.
Read the full story at AWS Machine Learning
The tools behind this win
- AWS TrainiumAI accelerator chips used to optimize Deepgram's voice model serving
- DeepgramSpeech-to-text, text-to-speech, and voice agent models