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.
Best for / Avoid if
Best for: Regulated or enterprise workloads - compliance attestations and an enterprise plan; AI agents and automation - an agent-ready surface (MCP / llms.txt); Teams needing broad API coverage out of the box
Avoid if: You want to try it free before paying
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
Other Speech-to-Text & Transcription APIs
ElevenLabs Scribe (Speech to Text)
"Scribe v2 is the most accurate Speech to Text model" offering "real-time Speech to Text in under 150 ms" across "90+ languages."
Azure AI Speech to Text
"Azure Speech in Foundry Tools provides speech to text, text to speech, and other capabilities through a Microsoft Foundry resource. You can transcribe speech to text with high accuracy, produce natural-sounding text-to-speech voices, translate spoken audio, and conduct live AI voice conversations."
Amazon Transcribe
"Amazon Transcribe is an automatic speech recognition service that uses machine learning models to convert audio to text. You can use Amazon Transcribe as a standalone transcription service or to add speech-to-text capabilities to any application."
Google Cloud Speech-to-Text
"Accurate voice typing and transcription powered by Gemini."
IBM watsonx Speech to Text
"IBM Watson® Speech to Text technology enables fast and accurate speech transcription in multiple languages for a variety of use cases, including but not limited to customer self-service, agent assistance and speech analytics."
AssemblyAI
"Voice AI infrastructure for developers building products that transcribe, understand, and act on speech."
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
- 2026-06-21 Capabilities: {} → {"self_hosted":true,"pii_redaction":true,"real_time_streaming":true,"speaker_di…
- 2026-06-15 Score Agent Friendliness: 45 → 40
- 2026-06-15 Score Docs Quality: 35 → 45
- 2026-06-15 Changelog URL: https://deepgram.com/changelog → https://docs.deepgram.com/changelog
- 2026-06-15 Robots Allows Agents: (none) → Yes
- 2026-06-15 Has Structured Data: (none) → No
- 2026-06-15 Llms Txt Present: Yes → No
- 2026-06-15 API Reference URL: (none) → https://docs.deepgram.com/reference/deepgram-api-overview
- 2026-06-09 Scoring Methodology: Scores are computed deterministically from this profile's published, sourced fi… → Scores are computed deterministically from this profile's published, sourced fi…
- 2026-06-09 Best For: Regulated or enterprise workloads — compliance attestations and an enterprise p… → Regulated or enterprise workloads - compliance attestations and an enterprise p…
- 2026-06-09 Score Trust Readiness: (none) → 85
- 2026-06-09 Score Agent Friendliness: (none) → 45
- 2026-06-09 Score Pricing Transparency: (none) → 60
- 2026-06-09 Score Setup Speed: (none) → 50
- 2026-06-09 Score Docs Quality: (none) → 35
- 2026-06-09 Score Procurement Friction: (none) → 75
- 2026-06-09 Scoring Methodology: (none) → Scores are computed deterministically from this profile's published, sourced fi…
- 2026-06-09 Best For: (none) → Regulated or enterprise workloads — compliance attestations and an enterprise p…
- 2026-06-09 Avoid If: (none) → You want to try it free before paying
- 2026-06-08 Llms Txt Present: (none) → Yes
- 2026-06-08 Docs URL: (none) → https://docs.deepgram.com
- 2026-06-08 Changelog URL: (none) → https://deepgram.com/changelog
- 2026-06-08 Status Page URL: (none) → https://status.deepgram.com
- 2026-06-08 Rendering: (none) → static
- 2026-06-08 Llms Txt URL: (none) → https://deepgram.com/llms.txt
- 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
Suggest an edit / leave a review
Leave a review or comment
curl -X POST https://apio.sh/api/feedback/deepgram \
-H 'Content-Type: application/json' \
-d '{"kind":"review","rating":5,"body":"Your experience with this API…"}'Suggest a correction to a field (cite a source)
curl -X POST https://apio.sh/api/suggest/deepgram/FIELD \
-H 'Content-Type: application/json' \
-d '{"value":"corrected value","citations":[{"url":"https://source.example/page","excerpt":"supporting quote"}],"note":"what changed and why"}'