ai-api
Deepgram pricing & features
Enterprise-grade speech-to-text + voice agents — Nova + Flux + Aura TTS
Enterprise STT + TTS + voice agents. Nova-3 (accurate) + Flux (fast streaming) + Aura TTS. $200 free credit, pay-as-you-go, Growth tier with prepay discounts, Enterprise with data residency.
Data sourced from vendor documentation · Last updated May 2026
Pricing
| Tier | Price | Notes |
|---|---|---|
| Pay-as-you-go | Free | $200 free credit. No minimums, no expiration. |
| Growth | $4000/mo | Starting $4K+/year prepay. Up to 20% savings. |
| Enterprise | Custom | Custom. Data residency, dedicated support, on-prem option. |
Limits
| Tier | Metric | Value | Notes |
|---|---|---|---|
| — | aura1 rate | $0.0150 per 1k chars (PAYG) | Aura-1 TTS |
| — | aura2 rate | $0.030 per 1k chars (PAYG) | Aura-2 TTS |
| — | diarization addon | $0.0020/min | Diarization |
| — | flux rate | $0.0077/min (PAYG) / $0.0065/min (Growth) | Flux model (streaming-optimized) |
| — | keyterm addon | $0.0013/min | Keyterm prompting |
| — | nova1 nova2 rate | $0.0058/min / $0.0047/min | Nova-1 / Nova-2 (cheaper) |
| — | nova3 mono rate | $0.0077/min / $0.0065/min | Nova-3 Monolingual |
| — | nova3 multi rate | $0.0092/min / $0.0078/min | Nova-3 Multilingual |
| — | redaction addon | $0.0020/min | PII redaction |
| — | smart formatting | Included free | Smart formatting |
| — | voice agent rate | $0.050-$0.163/min (by config) | Voice Agent API |
Features
- Aura TTS — Low-latency text-to-speech (<250ms). · docs
- Data Residency — EU / US / custom regions.
- Diarization — Speaker identification.
- Intent Detection — Detect speaker intents automatically.
- Keyterm Prompting — Boost accuracy for proper nouns + domain terms.
- Language Detection — Auto-detect spoken language.
- On-Prem Deployment — Enterprise: run Deepgram in your infra.
- PII Redaction — Auto-redact sensitive info.
- Pre-recorded STT — Transcribe audio/video files.
- Sentiment Analysis — Per-segment sentiment scores.
- Smart Format — Numbers, dates, times auto-formatted.
- Streaming STT — Realtime WebSocket-based transcription.
- Summarization — Automatic transcript summaries.
- Topic Detection — Auto-extract conversation topics.
- Voice Agent API — Unified STT + LLM + TTS for voice bots.
Developer interfaces
| Slug | Name | Kind | Version |
|---|---|---|---|
| sdk-node | @deepgram/sdk (Node) | sdk | 3.x |
| rest-api | Deepgram REST API | rest | v1 |
| streaming-ws | Streaming WebSocket | other | v1 |
| voice-agent | Voice Agent API | other | v1 |
| sdk-dotnet | deepgram-dotnet-sdk | sdk | 5.x |
| sdk-go | deepgram-go-sdk | sdk | 1.x |
| sdk-rust | deepgram-rust-sdk | sdk | 0.x |
| sdk-python | deepgram-sdk (Python) | sdk | 3.x |
Related ai-api platforms
ai-api
Anthropic API
API for Claude — frontier models for chat, tool use, agents, and long-context reasoning
ai-api
AssemblyAI
Best-in-class speech-to-text API — Universal models, 99 languages, low-latency streaming
ai-api
ElevenLabs
Best-in-class AI text-to-speech + voice cloning + Conversational AI
ai-api
Google Gemini API
Gemini 2.5 Pro, Flash, Flash-Lite — multimodal + 2M context
ai-api
Groq
Fastest LLM inference — LPU-powered (300-1000+ tokens/sec)
Compare Deepgram with
ai-api
Deepgram vs Anthropic API
Side-by-side breakdown.
ai-api
Deepgram vs AssemblyAI
Side-by-side breakdown.
ai-api
Deepgram vs ElevenLabs
Side-by-side breakdown.
ai-api
Deepgram vs Google Gemini API
Side-by-side breakdown.
ai-api
Deepgram vs Groq
Side-by-side breakdown.
ai-api
Deepgram vs OpenAI API
Side-by-side breakdown.
ai-api
Deepgram vs Replicate
Side-by-side breakdown.
ai-api
Deepgram vs Together AI
Side-by-side breakdown.
ai-coding
Deepgram vs Aider
Side-by-side breakdown.
ai-coding
Deepgram vs Bolt.new
Side-by-side breakdown.
ai-coding
Deepgram vs Claude Code
Side-by-side breakdown.
ai-coding
Deepgram vs Cody
Side-by-side breakdown.
Staxly is an independent catalog of developer platforms. The link to Deepgram above may be an affiliate link — Staxly may earn a commission if you sign up through it, at no extra cost to you. Pricing is verified at publication time — reconfirm on the vendor site before buying.