Deepgram
Build with the most accurate and cost-effective real-time APIs for speech-to-text, text-to-speech, and voice agents. Available in real-time and batch, cloud and self-hosted. [1]
Deepgram provides real-time and batch APIs for speech-to-text, text-to-speech, and voice agents, plus audio intelligence features like summarization. Pricing is usage-based, published, and self-serve. It offers webhooks, four SDKs, and an official MCP server, with availability in North America and Europe. The platform carries SOC 2 Type 2, HIPAA, GDPR, and PCI DSS compliance with a published SLA.
Scores
Pricing & procurement
- Pricing model
- Usage-based [2]
- Published pricing
- ✓ Yes [3]
- Free tier
- ✗ No [4]
- Free tier details
- $200 free credit, no minimums, no expiration, no credit card required [5]
- Self-serve signup
- ✓ Yes [6]
- Requires sales call
- ✗ No [7]
- Enterprise plan
- ✓ Yes [8]
- Minimum commitment
- $4K+ / year for Growth plan [9]
| Plan | Item | Per | Amount | Source |
|---|---|---|---|---|
| Free | Credit | account | $200 | source |
| Growth | Minimum commitment | year | $4000 | source |
| Pay As You Go | Flux English (Streaming) | minute | $0.0065 | source |
| Pay As You Go | Flux English (Pre-Recorded) | hour | $0.0077 | source |
| Growth | Flux English (Streaming) | minute | $0.0057 | source |
| Growth | Flux English (Pre-Recorded) | hour | $0.0065 | source |
| Pay As You Go | Flux Multilingual | minute | $0.0078 | source |
| Growth | Flux Multilingual | minute | $0.0068 | source |
| Pay As You Go | Nova-3 Monolingual (Streaming) | minute | $0.0048 | source |
| Pay As You Go | Nova-3 Monolingual (Pre-Recorded) | hour | $0.0077 | source |
| Growth | Nova-3 Monolingual (Streaming) | minute | $0.0042 | source |
| Growth | Nova-3 Monolingual (Pre-Recorded) | hour | $0.0065 | source |
| Pay As You Go | Nova-3 Multilingual (Streaming) | minute | $0.0058 | source |
| Pay As You Go | Nova-3 Multilingual (Pre-Recorded) | hour | $0.0092 | source |
| Growth | Nova-3 Multilingual (Streaming) | minute | $0.005 | source |
| Growth | Nova-3 Multilingual (Pre-Recorded) | hour | $0.0078 | source |
| Pay As You Go | Redaction | minute | $0.002 | source |
| Growth | Redaction | minute | $0.0017 | source |
| Pay As You Go | Keyterm Prompting | minute | $0.0013 | source |
| Growth | Keyterm Prompting | minute | $0.0012 | source |
| Pay As You Go | Speaker Diarization | minute | $0.002 | source |
| Growth | Speaker Diarization | minute | $0.0017 | source |
| Pay As You Go | Aura-2 | 1,000 characters | $0.03 | source |
| Growth | Aura-2 | 1,000 characters | $0.027 | source |
| Pay As You Go | Aura-1 | 1,000 characters | $0.015 | source |
| Growth | Aura-1 | 1,000 characters | $0.0135 | source |
| Pay As You Go | Voice Agent API Standard | minute | $0.075 | source |
| Growth | Voice Agent API Standard | minute | $0.068 | source |
| Pay As You Go | Voice Agent API Standard - BYO TTS | minute | $0.065 | source |
| Growth | Voice Agent API Standard - BYO TTS | minute | $0.051 | source |
| Pay As You Go | Voice Agent API Custom - BYO LLM | minute | $0.056 | source |
| Growth | Voice Agent API Custom - BYO LLM | minute | $0.059 | source |
| Pay As You Go | Voice Agent API Custom - BYO LLM + TTS | minute | $0.05 | source |
| Growth | Voice Agent API Custom - BYO LLM + TTS | minute | $0.041 | source |
| Pay As You Go | Voice Agent API Advanced | minute | $0.163 | source |
| Growth | Voice Agent API Advanced | minute | $0.146 | source |
| Pay As You Go | Voice Agent API Advanced - BYO TTS | minute | $0.122 | source |
| Growth | Voice Agent API Advanced - BYO TTS | minute | $0.11 | source |
| Pay As You Go | Summarization | 1,000 input tokens | $0.0003 | source |
| Pay As You Go | Summarization | 1,000 output tokens | $0.0006 | source |
| Growth | Summarization | 1,000 input tokens | $0.0002 | source |
| Growth | Summarization | 1,000 output tokens | $0.0005 | source |
Capabilities
- Supported actions
- transcribe_streaming_audio, transcribe_prerecorded_audio, synthesize_speech_rest, synthesize_speech_streaming, create_voice_agent, summarize_audio, summarize_text, detect_topics, detect_sentiment, detect_entities, detect_intents, detect_language, diarize_speakers, redact_content, smart_format, search_terms, keyterm_prompting, analyze_text, create_temporary_api_token, list_models, get_model_details, manage_projects, manage_members, manage_invitations, manage_scopes, manage_api_keys, view_billing_balances, view_usage_breakdown, view_request_history, manage_self_hosted_credentials [11]
- Regions
- North America, Europe [12]
- Languages
- Arabic, Belarusian, Bengali, Bosnian, Bulgarian, Catalan, Chinese (Cantonese), Chinese (Mandarin, Simplified), Chinese (Mandarin, Traditional), Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, Flemish, French, German, Greek, Gujarati, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Kannada, Korean, Latvian, Lithuanian, Macedonian, Malay, Marathi, Norwegian, Persian, Polish, Portuguese, Romanian, Russian, Serbian, Slovak, Slovenian, Spanish, Swedish, Tagalog, Tamil, Tamasheq, Telugu, Thai, Turkish, Ukrainian, Urdu, Vietnamese [13]
- Input types
- audio/wav, audio/webm, audio/ogg, audio/opus, audio/mulaw, audio/linear16 (raw PCM), audio/mp3, audio/flac, application/json, text/plain, SSML, multipart/form-data (file upload), binary audio stream [14]
- Output types
- JSON (transcripts, metadata, intelligence results, utterances), audio/wav, audio/mp3, audio/ogg; codec=opus, audio/flac, audio/pcm (raw) [15]
- Webhooks
- ✓ Yes [16]
- Sandbox / test mode
- ✗ No [17]
- SDK languages
- Python, JavaScript, Go, .NET [18]
- MCP server
- ✓ Yes [19]
Trust & compliance
- SOC 2
- SOC 2 Type II [20]
- HIPAA
- ✓ Yes [21]
- GDPR
- ✓ Yes [22]
- ISO 27001
- ✗ No [23]
- PCI DSS
- ✓ Yes [24]
- Published SLA
- ✓ Yes [25]
- Rate limits
- Concurrent connection limits per project varying by plan and region. Pay As You Go: STT Streaming up to 150 concurrent requests (NA), STT Pre-Recorded up to 50 concurrent requests, TTS REST up to 15 concurrent requests, TTS Streaming up to 45 concurrent requests, Voice Agent up to 45 concurrent connections, Audio Intelligence up to 10 concurrent requests. Growth: STT Streaming up to 225 concurrent requests (NA), Voice Agent up to 60 concurrent connections (NA). Limits vary by region (NA vs EU). Deepgram does not restrict the number of requests per time span, only the number of concurrent requests. [26]
- Known restrictions
- Secondary projects created on a self-serve account are limited to a single concurrent stream by design; bypassing rate limits this way violates Terms of Service, Temporary API keys are limited to 250 per day, Whisper Cloud is not available in the Europe region, Voice Agent API prices are calculated based on websocket connection time, Rates listed on pricing page opt in to the Model Improvement Program by default, On the Pay-As-You-Go plan, requests exceeding concurrency limit may be queued or rejected, Deepgram does not restrict the number of requests per time span, only the number of concurrent requests [27]
Developer surface
Integration
- Python
- JavaScript
- Go
- .NET
References
- ↑Description: deepgram.com
- ↑Pricing model: deepgram.com · aipedia.wiki
- ↑Published pricing: deepgram.com · aipedia.wiki
- ↑Free tier: deepgram.com
- ↑Free tier details: deepgram.com
- ↑Self-serve signup: developers.deepgram.com · developers.deepgram.com · playground.deepgram.com
- ↑Requires sales call: developers.deepgram.com · deepgram.com
- ↑Enterprise plan: deepgram.com · deepgram.com · deepgram.com
- ↑Minimum commitment: deepgram.com · fish.audio
- ↑Pricing: deepgram.com · blog.dograh.com · aipedia.wiki
- ↑Supported actions: developers.deepgram.com · deepgram.com · developers.deepgram.com · developers.deepgram.com · developers.deepgram.com
- ↑Regions: deepgram.com · deepgram.com
- ↑Languages: developers.deepgram.com · developers.deepgram.com · developers.deepgram.com · deepgram.com
- ↑Input types: developers.deepgram.com · developers.deepgram.com · developers.deepgram.com
- ↑Output types: developers.deepgram.com · developers.deepgram.com
- ↑Webhooks: developers.deepgram.com · developers.deepgram.com · developers.deepgram.com · developers.deepgram.com
- ↑Sandbox: playground.deepgram.com · deepgram.com
- ↑SDK languages: developers.deepgram.com · github.com · npmjs.com · github.com · developers.deepgram.com
- ↑MCP server: developers.deepgram.com · developers.deepgram.com
- ↑SOC 2: developers.deepgram.com · deepgram.com
- ↑HIPAA: developers.deepgram.com · accountablehq.com
- ↑GDPR: developers.deepgram.com · nudgesecurity.com · developers.deepgram.com
- ↑ISO 27001: developers.deepgram.com · deepgram.com
- ↑PCI DSS: developers.deepgram.com · deepgram.com
- ↑Published SLA: deepgram.com · deepgram.com · status.deepgram.com
- ↑Rate limits: developers.deepgram.com · developers.deepgram.com · developers.deepgram.com · developers.deepgram.com
- ↑Known restrictions: developers.deepgram.com · developers.deepgram.com · fish.audio
Change history
- 2026-06-08 Docs URL: (none) → https://docs.deepgram.com
- 2026-06-08 Status Page URL: (none) → https://status.deepgram.com
- 2026-06-08 Changelog URL: (none) → https://deepgram.com/changelog
- 2026-06-08 Llms Txt Present: (none) → Yes
- 2026-06-08 Llms Txt URL: (none) → https://deepgram.com/llms.txt
- 2026-06-08 Rendering: (none) → static
- 2026-06-07 Summary Md: (none) → Deepgram provides real-time and batch APIs for speech-to-text, text-to-speech, …
- 2026-06-07 SDK Packages: (none) → Python, JavaScript, Go, .NET