OpenAI Text to Speech (gpt-4o-mini-tts / tts-1)

Best for: Regulated or enterprise workloads - compliance attestations and an enterprise plan; Cost-sensitive teams - low, transparent entry price

Avoid if: You want to try it free before paying

Pricing model

Usage-based [2]developers.openai.com/api/docs/models/gpt-4o-mini-tts“Input: $0.60 per 1M text tokens; Output: $12.00 per 1M audio tokens”developers.openai.com/api/docs/models/tts-1“$15.00 per 1M characters for speech generation”

Published pricing

✓ Yes [3]developers.openai.com/api/docs/models/tts-1-hd“$30.00 per 1 million characters”developers.openai.com/api/docs/models/tts-1“$15.00 per 1M characters”

Free tier

✗ No [4]developers.openai.com/api/docs/models/tts-1“Free tier: 3 RPM, 200 RPD — this is a rate-limit tier, not a recurring free-character allowance”

Self-serve signup

✓ Yes

Requires sales call

✗ No

Enterprise plan

✓ Yes

• Real-time streaming
• Voice design

Supported actions

synthesize_speech, streaming_tts, voice_design, speed_control, instruction_based_voice_control, realtime_tts, custom_voice_creation [5]developers.openai.com/api/docs/guides/text-to-speech“The gpt-4o-mini-tts model accepts instructions to control accent, emotional range, intonation, impressions, speech speed, tone, and whispering.”developers.openai.com/api/docs/guides/text-to-speech“Organizations can create up to 20 custom voices from audio samples (≤30 seconds), though this requires special eligibility.”

Languages

Afrikaans, Arabic, Armenian, Azerbaijani, Belarusian, Bosnian, Bulgarian, Catalan, Chinese, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, Galician, German, Greek, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Kannada, Kazakh, Korean, Latvian, Lithuanian, Macedonian, Malay, Marathi, Maori, Nepali, Norwegian, Persian, Polish, Portuguese, Romanian, Russian, Serbian, Slovak, Slovenian, Spanish, Swahili, Swedish, Tagalog, Tamil, Thai, Turkish, Ukrainian, Urdu, Vietnamese, Welsh [6]developers.openai.com/api/docs/guides/text-to-speech“The API generally follows the Whisper model in terms of language support. Includes: Afrikaans, Arabic, Armenian, Azerbaijani, Belarusian, Bosnian, Bulgarian, Catalan, Chinese, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, Galician, German, Greek, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Kannada, Kazakh, Korean, Latvian, Lithuanian, Macedonian, Malay, Marathi, Maori, Nepali, Norwegian, Persian, Polish, Portuguese, Romanian, Russian, Serbian, Slovak, Slovenian, Spanish, Swahili, Swedish, Tagalog, Tamil, Thai, Turkish, Ukrainian, Urdu, Vietnamese, Welsh.”

Input types

plain text

Output types

mp3, opus, aac, flac, wav, pcm [7]developers.openai.com/api/reference/resources/audio/subresources/speech/methods/create“response_format: mp3, opus, aac, flac, wav, pcm”

Webhooks

✗ No [8]developers.openai.com/api/docs/guides/text-to-speech“The TTS API is a request-based API that generates audio directly in response to API calls; no webhook mechanism is used for standard TTS endpoints.”

Sandbox / test mode

✗ No

SDK languages

Python, Node.js, Java, Go, Ruby, .NET [9]developers.openai.com/api/docs/libraries“Official SDKs: JavaScript/TypeScript (npm), Python (pip), C#/.NET (NuGet, in collaboration with Microsoft), Java (Maven, beta), Go (beta), Ruby (gem)”

MCP server

✗ No [10]developers.openai.com/api/docs/docs-mcp“The MCP server provides read-only access to OpenAI developer documentation (search + page content) — not a TTS action server.”

SOC 2

SOC 2 Type II [11]trust.openai.com“SOC 2 Type 2 (covering Security, Availability, Confidentiality, and Privacy). SOC 2 Type 2 report available for period Jan 1 - Jun 30, 2025.”

HIPAA

✓ Yes [12]openai.com/api/“Business Associate Agreements for HIPAA compliance available for eligible customers.”help.openai.com/en/articles/8660679-how-can-i-get-a-business-associate-agreement-baa-with-openai-for-the-api-services“OpenAI is able to sign Business Associate Agreements (BAA) in support of customers' compliance with HIPAA. Most API services are covered by the BAA.”

GDPR

✓ Yes [13]trust.openai.com“GDPR compliance”

ISO 27001

✓ Yes [14]trust.openai.com“ISO/IEC 27001:2022 — certificate documents operation of an Information Security Management System that conforms to ISO/IEC 27001:2022 for OpenAI's API, ChatGPT Enterprise, and ChatGPT Edu services.”

PCI DSS

✓ Yes [15]trust.openai.com“PCI DSS v4.0.1 (for payment processing components)”

Published SLA

✓ Yes [16]openai.com/api-scale-tier/“Scale Tier traffic offers a 99.9% uptime SLA and prioritized compute.”

Rate limits

tts-1/tts-1-hd: Free 3 RPM / 200 RPD; Tier 1: 500 RPM; Tier 2: 2,500 RPM; Tier 3: 5,000 RPM; Tier 4: 7,500 RPM; Tier 5: 10,000 RPM. gpt-4o-mini-tts: Tier 1 500 RPM / 50,000 TPM; Tier 5 10,000 RPM / 8,000,000 TPM. [17]developers.openai.com/api/docs/models/gpt-4o-mini-tts“Tier 1: 500 RPM / 50,000 TPM; Tier 5: 10,000 RPM / 8,000,000 TPM”developers.openai.com/api/docs/models/tts-1“Rate Limits by Tier: Free: 3 RPM, Tier 1: 500 RPM, Tier 2: 2,500 RPM, Tier 3: 5,000 RPM, Tier 4: 7,500 RPM, Tier 5: 10,000 RPM”

Known restrictions

Maximum input length: 4096 characters per request (tts-1/tts-1-hd); 2,000 tokens for gpt-4o-mini-tts, Custom voices limited to up to 20 per organization; requires eligibility and sales contact, Custom voice audio samples must be 30 seconds or less, Instructions parameter (voice control) not available on tts-1 or tts-1-hd; only gpt-4o-mini-tts, SSE stream_format not available for tts-1/tts-1-hd, Usage policies require clear disclosure to end users that TTS voice is AI-generated, Custom voice consent phrases required in specific languages, SSML not supported, Speed parameter range: 0.25 to 4.0 [18]developers.openai.com/api/reference/resources/audio/subresources/speech/methods/create“The maximum length is 4096 characters for the input text parameter.”developers.openai.com/api/docs/guides/text-to-speech“Usage policies require clear disclosure to end users that the TTS voice they are hearing is AI-generated and not a human voice.”

• Docs
• API reference

Docs rendering: static · markdown variants served

API style

rest

Base URL

https://api.openai.com/v1

Version

v1

Versioning

url

Stability

ga

Auth methods

api_key

Idempotency keys

✗ No

Error format

vendor-specific

Rate limit

500 / minute

SDKs

• Python openai · repo
• Node.js openai · repo
• Java openai-java · repo
• Go openai-go · repo
• Ruby openai · repo
• .NET OpenAI · repo

• Auth docs
• Quickstart
• MCP server
• Deprecation policy

Launched

2023-11-06

GA

2023-11-06

• 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

OpenAI Text to Speech (gpt-4o-mini-tts / tts-1) alternatives · OpenAI Text to Speech (gpt-4o-mini-tts / tts-1) 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: developers.openai.com
2. ↑Pricing model: developers.openai.com · developers.openai.com
3. ↑Published pricing: developers.openai.com · developers.openai.com
4. ↑Free tier: developers.openai.com
5. ↑Supported actions: developers.openai.com · developers.openai.com
6. ↑Languages: developers.openai.com
7. ↑Output types: developers.openai.com
8. ↑Webhooks: developers.openai.com
9. ↑SDK languages: developers.openai.com
10. ↑MCP server: developers.openai.com
11. ↑SOC 2: trust.openai.com
12. ↑HIPAA: openai.com · help.openai.com
13. ↑GDPR: trust.openai.com
14. ↑ISO 27001: trust.openai.com
15. ↑PCI DSS: trust.openai.com
16. ↑Published SLA: openai.com
17. ↑Rate limits: developers.openai.com · developers.openai.com
18. ↑Known restrictions: developers.openai.com · developers.openai.com

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

1. 2026-06-21 Capabilities: {} → {"streaming":true,"voice_design":true}
2. 2026-06-21 Summary Md: (none) → OpenAI Text to Speech converts text into lifelike spoken audio via three models…
3. 2026-06-21 Score Agent Friendliness: (none) → 30
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) → 50
7. 2026-06-21 Score Procurement Friction: (none) → 85
8. 2026-06-21 Score Trust Readiness: (none) → 100
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 Robots Allows Agents: (none) → Yes
13. 2026-06-21 API Reference URL: (none) → https://platform.openai.com/api/reference/overview
14. 2026-06-21 Markdown Docs Served: (none) → Yes
15. 2026-06-21 Markdown Docs URL: (none) → https://platform.openai.com/docs/guides/text-to-speech.md
16. 2026-06-21 Docs URL: (none) → https://developers.openai.com/api/docs
17. 2026-06-21 Has Structured Data: (none) → No
18. 2026-06-21 Llms Txt Present: (none) → No
19. 2026-06-21 Rendering: (none) → static
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 ISO 27001: set to Yes
27. 2026-06-21 PCI DSS: set to Yes
28. 2026-06-21 SLA Published: set to Yes
29. 2026-06-21 SLA URL: set to https://openai.com/api-scale-tier/
30. 2026-06-21 Data Retention Policy URL: set to https://developers.openai.com/api/docs/guides/your-data
31. 2026-06-21 Documented Rate Limits: set to tts-1/tts-1-hd: Free 3 RPM / 200 RPD; Tier 1: 500 RPM; Tier 2: 2,500 RPM; Tier …
32. 2026-06-21 Rate Limit Requests: set to 500
33. 2026-06-21 Rate Limit Window: set to minute
34. 2026-06-21 Known Restrictions: set to Maximum input length: 4096 characters per request (tts-1/tts-1-hd); 2,000 token…
35. 2026-06-21 Auth Methods: set to api_key
36. 2026-06-21 Auth Docs URL: set to https://developers.openai.com/api/reference/overview
37. 2026-06-21 API Style: set to rest
38. 2026-06-21 Base URL: set to https://api.openai.com/v1
39. 2026-06-21 API Version: set to v1
40. 2026-06-21 Versioning Scheme: set to url
41. 2026-06-21 Stability: set to ga
42. 2026-06-21 Deprecation Policy URL: set to https://developers.openai.com/api/docs/deprecations
43. 2026-06-21 MCP URL: set to https://developers.openai.com/mcp
44. 2026-06-21 Quickstart URL: set to https://developers.openai.com/api/docs/guides/text-to-speech
45. 2026-06-21 Idempotency Supported: set to No
46. 2026-06-21 Error Format: set to vendor-specific
47. 2026-06-21 Requires Verification: set to No
48. 2026-06-21 Slug: set to openai-tts
49. 2026-06-21 Price Basis: set to 1M characters
50. 2026-06-21 Launched At: set to 2023-11-06

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/openai-tts \
  -H 'Content-Type: application/json' \
  -d '{"kind":"review","rating":5,"body":"Your experience with this API…"}'

curl -X POST https://apio.sh/api/suggest/openai-tts/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 →