MoreAI.tools
Deepgram preview
80
Stack Score
Editorial pick
Deepgram logo

Deepgram

Production-grade speech-to-text.

Try Deepgram✓ Free trial available

Best for

Developers building voice products at scale who need streaming, diarization, and predictable per-minute economics.

At a glance

Pricing
freemium
Setup time
15 minutes
Learning curve
medium
Last verified
5/19/2026

What we love

  • Streaming + diarization out of the box is the right default for call audio
  • Latency is genuinely fast enough for live conversational use cases
  • $200 free credit lets you test seriously before committing

Where it falls short

  • Accuracy in noisy or accented audio still trails Whisper-large-v3
  • Pricing per minute adds up at high volume — negotiate enterprise rates
  • Domain-specific finetuning requires the higher tier

Pricing

✓ Pricing verified Jun 21, 2026

3 tiers

Pay as you go

From $0.0043

per minute streaming

  • $200 free credit
  • Nova-3 model
  • Diarization

Growth

$4,000

annual commit

  • Discounted rates
  • Priority support
  • Higher rate limits

Enterprise

Custom

contact sales

  • On-prem deployment
  • Custom models
  • SLA

Why we picked it

When Whisper isn't fast enough and you need streaming, Deepgram's the upgrade.
— MoreAI.tools editor

Overview

Fast, accurate ASR with streaming, diarization, and a strong free tier ($200 credit). Built for production call centers and live transcription.

Key features

  • Nova-3 model — fastest production ASR with high accuracy
  • Real-time streaming transcription with sub-300ms latency
  • Speaker diarization out of the box
  • Multilingual support with language detection
  • Aura TTS — text-to-speech for full voice-AI pipelines
  • Generous $200 free credit on signup, no card required

Best use cases

Live call transcription

Stream contact-center audio into text in real time with speaker labels for QA and coaching.

Meeting note pipelines

Transcribe Zoom or Meet calls with diarization for downstream LLM summarization.

Voice agent backbone

Feed STT into a Cartesia + LLM stack for full conversational voice products.

Integrations

Twilio
Zoom
Microsoft Teams
LiveKit
Pipecat
LangChain
Vapi

One AI Stack pick every week.

The tool we’d pay for this week, why we’d pay for it, and what we’d skip. No promo spam.