Deepgram Documentation

Find the right docs for what you're building with Deepgram.

Ask AI

Have a question? Get answers from Deepgram's AI assistant at https://developers.deepgram.com/ask-ai.

Documentation by Topic

Speech-to-Text (STT)

Transcribe audio and video into text. Deepgram ships two actively maintained, next-gen model families — pick the one that matches your use case.

• Nova (/v1/listen) — general-purpose transcription (captions, subtitles, batch files, live streams). Rich feature set including intelligence overlays (diarize, summarize, sentiment, topics, intents).
• Flux (/v2/listen) — conversational-audio transcription for voice agents and interactive assistants. Built-in turn-taking (EOT events, mid-session reconfig).

Docs:

• STT Getting Started (Nova)