Deepgram
Deepgram provides speech-to-text as a clean developer API: fast, accurate transcription models with word-level timestamps, diarization, and streaming support. It powers the voice features in Replicator, turning spoken input into text that the rest of an LLM pipeline can work with — transcription as infrastructure rather than a product bolted on.
How We Use It
- Voice input for LLM-powered editing and content workflows
- Accurate transcription with word-level timestamps and diarization
- Streaming speech-to-text for responsive voice interfaces
AI / LLM
Why this matters: Controversial, misunderstood, and overhyped though they may be, AI and LLMs are transforming industries and society. Used carefully and responsibly, they are still a valuable tool for innovation and progress. We design and deploy LLM-powered features with a focus on safety, performance, and maintainability, leveraging managed model providers and an SDK-first approach for rapid iteration. Preferred defaults: Vercel AI SDK + AI Gateway for multi-model orchestration; Anthropic and OpenAI as primary model providers.