Voice and music · by Deepgram

Deepgram

Transcribe speech live and know when the speaker has finished talking.

speech, link → text, data · speech → text, events · speech, text → data, text
Way in
Official APISign up yourself, api key
To start
$$200 non-expiring credit, no card (~43k Nova-3 minutes)
Runs
In the cloud
Checked
Nov 3, 2026Prices as of that day

What it can do 3

Transcribe recorded audio with timestamps and diarizationper-second billing, no minimumsspeech, link → text, data$0.0043/min (Nova-3 mono, prerecorded); $0.0052/min multilingual
Stream live transcription with end-of-turn detection for voice agentsWebSocketspeech → text, events$0.0077/min (Flux English or Nova-3 streaming)
Summarize, detect topics, sentiment and intent from transcriptsspeech, text → data, text$0.0003/1k input tokens + $0.0006/1k output tokens on top of STT

Does the same job

Prices and limits as of Nov 3, 2026, from Deepgram’s own pages. They change; check before you rely on them.Not affiliated with Deepgram. Not advice.Rankings: Artificial Analysis.Something wrong?
Made by Jasper Burns

A short note when I ship something new, about once a month. One list for all my projects.