IBM

IBM selected Deepgram as its first fully embedded third-party speech model provider after customers asked for higher-accuracy STT and TTS, lower latency, and more flexible deployment than traditional cloud speech services could deliver. Deepgram's speech-to-text and text-to-speech models are now embedded into IBM watsonx, giving enterprises a modern voice AI stack on top of IBM's infrastructure.

By embedding Deepgram inside watsonx Orchestrate Agent Builder, IBM clients can build voice agents and voice-enabled workflows on top of a real-time speech foundation that has been refined over more than a decade. Customers tap Deepgram's STT and TTS capabilities directly through their existing IBM environment, without adding extra vendors or commercial complexity.

The integration covers contact-center conditions (accents, background noise, alphanumeric read-back) where speech accuracy makes the call usable, latency low enough to feel like a real conversation, and deployment across IBM Cloud, customer VPC, and self-hosted on regulated infrastructure. The integration is announced via joint press release and shipping inside watsonx Orchestrate today.

If you are running IBM watsonx Orchestrate and evaluating voice, the integration is built in. Reach out via deepgram.com/contact-us for enterprise terms.

• Deepgram and IBM Introduce Advanced Voice Capabilities for Enterprise AI
• Deepgram × IBM: Enterprise Voice AI Inside watsonx CX
• IBM watsonx Orchestrate
• Powered by Deepgram
• Contact Deepgram