Deepgram Aura (Text to Speech)

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 model

Usage-based [2]deepgram.com/pricing“Pay As You Go: Aura-2: $0.030/1k characters; Aura-1: $0.0150/1k characters”deepgram.com/pricing“Growth option allows customers to Save up to 20% by committing to prepaid annual credits that are redeemed against actual usage — no mandatory recurring base fee on the standard Pay As You Go tier”

Published pricing

✓ Yes [3]deepgram.com/pricing“Aura-2: $0.030/1k characters; Aura-1: $0.0150/1k characters”

Free tier

✗ No [4]deepgram.com/pricing“Free $200 Credit — no credit card required to start. Provides access to All endpoints in public models for Speech-to-Text and Text-to-Speech services.”

Self-serve signup

✓ Yes

Requires sales call

✗ No

Enterprise plan

✓ Yes [5]deepgram.com/pricing“Enterprise — For businesses with large volumes, data or deployment requirements, or support needs.”

• Real-time streaming
• Multilingual voices

Supported actions

synthesize_speech, streaming_tts, websocket_streaming, rest_tts, tts_callback, audio_output_streaming, multilingual_synthesis, codeswitching_voices, self_hosted_deployment

Regions

United States, European Union (api.eu.deepgram.com), Australia (api.au.deepgram.com) [6]developers.deepgram.com/trust-security/data-privacy-compliance“European Union: api.eu.deepgram.com; Australia: api.au.deepgram.com (AWS ap-southeast-2, Sydney)”

Languages

English (US), English (UK/British), English (Australian), English (Irish), English (Filipino/Philippine), Spanish (Mexican), Spanish (Peninsular), Spanish (Colombian), Spanish (Latin American), German, French, Dutch, Italian, Japanese [7]developers.deepgram.com/docs/tts-models“Aura-2 offers the most extensive voice library: English (39 voices), Spanish (17 voices, Early Access), Dutch (9 voices), French (2 voices), German (7 voices), Italian (10 voices), Japanese (5 voices)”

Input types

plain text, JSON text payload

Output types

mp3, wav/linear16, mulaw, alaw, opus, flac, aac, streaming audio chunks [8]developers.deepgram.com/docs/tts-encoding“linear16: 16-bit, little-endian, signed PCM WAV data; mulaw: Mu-law encoded WAV data; alaw: A-law encoded WAV data; mp3: MP3 audio compression format (default); opus: Ogg Opus codec; flac: Free Lossless Audio Codec (FLAC); aac: Advanced Audio Coding format”

Webhooks

✓ Yes [9]developers.deepgram.com/docs/tts-callback“Deepgram's Callback feature allows you to supply a callback URL to which generated text-to-speech audio can be returned. When passed, Deepgram will immediately respond with a request_id before processing your text asynchronously.”

Sandbox / test mode

✗ No [10]developers.deepgram.com/docs/create-additional-api-keys“For best results, use different API keys for testing and production. [No separate sandbox environment — testing occurs in the live environment using the $200 trial credit]”

SDK languages

JavaScript, Python, Go, .NET [11]developers.deepgram.com/docs/text-to-speech“JavaScript/Node.js, Python, Go, C#, Java”

MCP server

✓ Yes [12]developers.deepgram.com/developer-tools/cli/mcp-server“The dg CLI includes a built-in MCP (Model Context Protocol) server that gives AI coding tools direct access to Deepgram APIs.”

SOC 2

SOC 2 Type II [13]developers.deepgram.com/trust-security/data-privacy-compliance“Deepgram has achieved SOC 2 Type 1 and Type 2 certification.”deepgram.com/data-security“We recently received a SOC 2 Type II 'clean bill of health' from Cyberguard Compliance—the gold standard in SOC audits.”

HIPAA

✓ Yes [14]developers.deepgram.com/trust-security/data-privacy-compliance“Deepgram is considered a Business Associate as defined by the US HIPAA legislation.”developers.deepgram.com/trust-security/security-policy“We maintain HIPAA Compliance and are PCI Compliant, adhering to the requirements throughout the year, which includes a list of checks, obligations, and independent audits for verification.”

GDPR

✓ Yes [15]developers.deepgram.com/trust-security/data-privacy-compliance“Deepgram is GDPR ready and provides information to customers to help them understand how features and functionality of its platform may affect their GDPR compliance obligations. For customers requiring data processing within the European Union, Deepgram provides an EU-specific endpoint at api.eu.deepgram.com.”

ISO 27001

– Unknown [16]developers.deepgram.com/trust-security/data-privacy-compliance“Deepgram has achieved SOC 2 Type 1 and Type 2 certification. [ISO 27001 is not mentioned on any trust/security page]”

PCI DSS

✓ Yes [17]developers.deepgram.com/trust-security/security-policy“We maintain HIPAA Compliance and are PCI Compliant, adhering to the requirements throughout the year, which includes a list of checks, obligations, and independent audits for verification.”developers.deepgram.com/trust-security/data-privacy-compliance“We are PCI compliant, and perform a yearly review of our standing within the framework.”

Published SLA

✓ Yes [18]deepgram.com/dedicated“Get predictable latency and 99.9% uptime, backed by enterprise-grade SLAs.”

Rate limits

Max 2,000 characters per request (Aura-2 and Aura-1); requests exceeding this return HTTP 413. Concurrent request limit enforced per project: 15 concurrent REST requests on Pay As You Go; 45 concurrent WebSocket requests. Exceeding returns HTTP 429 Too Many Requests. [19]developers.deepgram.com/reference/api-rate-limits“Text-to-Speech REST: 15 concurrent (Aura/Aura-2) — Pay as You Go plan”developers.deepgram.com/docs/text-to-speech“Aura-2 and Aura-1 models: Maximum 2,000 characters. Exceeding this triggers a 413 error.”

Known restrictions

No SSML support; uses text-based prompting techniques (punctuation, filler words) for speech control instead, WebSocket/streaming mode only supports linear16, mulaw, and alaw encodings; compressed formats (mp3, opus, flac, aac) are REST-only, Maximum 2,000 characters per REST request, $200 sign-up credit is a one-time trial credit, not a recurring free tier, Voice cloning not offered as a self-serve feature, Spanish, Dutch, French, German, Italian, Japanese voices are Aura-2 only (Aura-1 has English voices only) [20]developers.deepgram.com/docs/tts-encoding“streaming audio output is only available with the PCM and mu-law/a-law formats, while the compressed formats (MP3, Opus, FLAC, AAC) work exclusively with REST requests.”developers.deepgram.com/docs/tts-models“Aura 1 (legacy) includes 12 English voices only; Spanish, Dutch, French, German, Italian, Japanese voices are Aura-2 only”

• Docs
• llms.txt
• Changelog
• Status page

Docs rendering: static · llms.txt present

API style

rest

Base URL

https://api.deepgram.com/v1

Version

v1

Versioning

url

Stability

ga

Auth methods

api_key, jwt

Error format

vendor-specific

Webhook signing

dg-token header

Rate limit

15 / concurrent

SDKs

• JavaScript @deepgram/sdk · repo
• Python deepgram-sdk · repo
• Go github.com/deepgram/deepgram-go-sdk/v2 · repo
• .NET Deepgram · repo

• Auth docs
• Quickstart
• MCP server
• Webhook events

Launched

2024-03-12

GA

2024-03-12

Notable customers

Humach, Vapi, Daily, Twilio, Quiq

• ElevenLabs Text to Speech

  "Text to Speech with high quality, human-like AI voices"

  Hybrid · free tier · public pricing · self-serve

• Azure AI Text to Speech

  "Text to speech enables your applications, tools, or devices to convert text into human like synthesized speech. The text to speech capability is also known as speech synthesis. Use human like standard voices out of the box, or create a custom voice that's unique to your product or brand."

  Usage · free tier · public pricing · self-serve

• Amazon Polly

  "Amazon Polly is a cloud service that converts text into lifelike speech. You can use Amazon Polly to develop applications that increase engagement and accessibility."

  Usage · free tier · public pricing · self-serve

• Google Cloud Text-to-Speech

  "Cloud Text-to-Speech converts text or Speech Synthesis Markup Language (SSML) input into audio data of natural human speech."

  Usage · free tier · public pricing · self-serve

• Cartesia (Sonic)

  "The fastest and most natural text to speech model"

  Hybrid · free tier · public pricing · self-serve

• Murf AI

  "Enterprise-grade AI voice generation with 150+ natural-sounding voices across 35 languages and 20+ speaking styles."

  Usage · public pricing · self-serve

Deepgram Aura (Text to Speech) alternatives · Deepgram Aura (Text to Speech) vs ElevenLabs Text to Speech · All Text-to-Speech APIs APIs

Each field above carries a numbered source - hover for a preview, click to jump here.

1. ↑Description: deepgram.com
2. ↑Pricing model: deepgram.com · deepgram.com
3. ↑Published pricing: deepgram.com
4. ↑Free tier: deepgram.com
5. ↑Enterprise plan: deepgram.com
6. ↑Regions: developers.deepgram.com
7. ↑Languages: developers.deepgram.com
8. ↑Output types: developers.deepgram.com
9. ↑Webhooks: developers.deepgram.com
10. ↑Sandbox: developers.deepgram.com
11. ↑SDK languages: developers.deepgram.com
12. ↑MCP server: developers.deepgram.com
13. ↑SOC 2: developers.deepgram.com · deepgram.com
14. ↑HIPAA: developers.deepgram.com · developers.deepgram.com
15. ↑GDPR: developers.deepgram.com
16. ↑ISO 27001: developers.deepgram.com
17. ↑PCI DSS: developers.deepgram.com · developers.deepgram.com
18. ↑Published SLA: deepgram.com
19. ↑Rate limits: developers.deepgram.com · developers.deepgram.com
20. ↑Known restrictions: developers.deepgram.com · developers.deepgram.com

Every field change, who made it, and when - from our audited data pipeline and editors.

1. 2026-06-21 Capabilities: {} → {"streaming":true,"multilingual":true}
2. 2026-06-21 Summary Md: (none) → Deepgram Aura is a streaming text-to-speech API built for real-time voice agent…
3. 2026-06-21 Score Agent Friendliness: (none) → 55
4. 2026-06-21 Score Pricing Transparency: (none) → 85
5. 2026-06-21 Score Setup Speed: (none) → 60
6. 2026-06-21 Score Docs Quality: (none) → 35
7. 2026-06-21 Score Procurement Friction: (none) → 85
8. 2026-06-21 Score Trust Readiness: (none) → 85
9. 2026-06-21 Best For: (none) → Regulated or enterprise workloads - compliance attestations and an enterprise p…
10. 2026-06-21 Avoid If: (none) → You want to try it free before paying
11. 2026-06-21 Scoring Methodology: (none) → Scores are computed deterministically from this profile's published, sourced fi…
12. 2026-06-21 Has Structured Data: (none) → No
13. 2026-06-21 Robots Allows Agents: (none) → Yes
14. 2026-06-21 Status Page URL: (none) → https://status.deepgram.com
15. 2026-06-21 Changelog URL: (none) → https://deepgram.com/changelog
16. 2026-06-21 Docs URL: (none) → https://developers.deepgram.com/home
17. 2026-06-21 Rendering: (none) → static
18. 2026-06-21 Llms Txt Present: (none) → Yes
19. 2026-06-21 Llms Txt URL: (none) → https://deepgram.com/llms.txt
20. 2026-06-21 Self Serve Signup: set to Yes
21. 2026-06-21 Requires Sales Call: set to No
22. 2026-06-21 Enterprise Plan Available: set to Yes
23. 2026-06-21 SOC 2: set to type_2
24. 2026-06-21 HIPAA: set to Yes
25. 2026-06-21 GDPR: set to Yes
26. 2026-06-21 PCI DSS: set to Yes
27. 2026-06-21 SLA Published: set to Yes
28. 2026-06-21 Data Retention Policy URL: set to https://developers.deepgram.com/trust-security/data-privacy-compliance
29. 2026-06-21 Documented Rate Limits: set to Max 2,000 characters per request (Aura-2 and Aura-1); requests exceeding this r…
30. 2026-06-21 Rate Limit Requests: set to 15
31. 2026-06-21 Rate Limit Window: set to concurrent
32. 2026-06-21 Known Restrictions: set to No SSML support; uses text-based prompting techniques (punctuation, filler word…
33. 2026-06-21 Auth Methods: set to api_key, jwt
34. 2026-06-21 Auth Docs URL: set to https://developers.deepgram.com/reference/authentication
35. 2026-06-21 API Style: set to rest
36. 2026-06-21 Base URL: set to https://api.deepgram.com/v1
37. 2026-06-21 API Version: set to v1
38. 2026-06-21 Versioning Scheme: set to url
39. 2026-06-21 Stability: set to ga
40. 2026-06-21 MCP URL: set to https://developers.deepgram.com/_mcp/server
41. 2026-06-21 Quickstart URL: set to https://developers.deepgram.com/docs/text-to-speech
42. 2026-06-21 Error Format: set to vendor-specific
43. 2026-06-21 Webhook Signing: set to dg-token header
44. 2026-06-21 Webhook Events URL: set to https://developers.deepgram.com/docs/tts-callback
45. 2026-06-21 Requires Verification: set to No
46. 2026-06-21 Starting Price Usd: set to 0
47. 2026-06-21 Slug: set to deepgram-aura
48. 2026-06-21 Free Tier Limit: set to $200 credit
49. 2026-06-21 Launched At: set to 2024-03-12
50. 2026-06-21 GA Date: set to 2024-03-12

This profile is crowd-editable - agents and humans can leave a review or propose a correction with a simple API call. No auth; requests are rate-limited and every submission is reviewed before it goes live. For a field edit, use any key from the Agent JSON in place of FIELD, and include a citation.

curl -X POST https://apio.sh/api/feedback/deepgram-aura \
  -H 'Content-Type: application/json' \
  -d '{"kind":"review","rating":5,"body":"Your experience with this API…"}'

curl -X POST https://apio.sh/api/suggest/deepgram-aura/FIELD \
  -H 'Content-Type: application/json' \
  -d '{"value":"corrected value","citations":[{"url":"https://source.example/page","excerpt":"supporting quote"}],"note":"what changed and why"}'

All the ways to contribute →