Azure AI Text to Speech

Best for: Prototypes and side projects - free to start, no sales call; Regulated or enterprise workloads - compliance attestations and an enterprise plan; AI agents and automation - an agent-ready surface (MCP / llms.txt)

Pricing model

Usage-based [2]azure.microsoft.com/en-us/pricing/details/speech/learn.microsoft.com/en-us/azure/ai-services/speech-service/text-to-speech“When you use the text to speech feature, billing is based on the total number of characters in each successfully processed request.”

Published pricing

✓ Yes [3]azure.microsoft.com/en-us/pricing/details/speech/

Free tier

✓ Yes [4]speechify.com/blog/microsoft-azure-pricing-plans/“Limited to processing 0.5 million characters per month”learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-services-quotas-and-limits“For the Free (F0) pricing tier, see the monthly allowances on the pricing page.”

Free tier details

Free (F0) tier: 0.5 million characters per month for neural text-to-speech (recurring monthly allowance, not a one-time trial). Free tier rate limits are not adjustable.

Self-serve signup

✓ Yes

Requires sales call

✗ No

Enterprise plan

✓ Yes [5]learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-services-quotas-and-limits“For Standard pricing tier, you can increase the real-time TPS limit. A TPS increase request requires business justification.”

• Real-time streaming
• Voice cloning
• Voice design
• SSML control
• Multilingual voices
• Word timestamps

Supported actions

synthesize_speech, streaming_tts, batch_synthesis, ssml_support, word_timestamps, viseme_generation, professional_voice_cloning, personal_voice_cloning, custom_voice_training, multilingual_synthesis, voice_design, audio_content_creation, text_to_speech_avatar, real_time_synthesis, async_long_audio_synthesis [6]learn.microsoft.com/en-us/azure/ai-services/speech-service/text-to-speech“Improve text to speech output with SSML: Speech Synthesis Markup Language (SSML) is an XML-based markup language used to customize text to speech outputs. Visemes: Visemes are the key poses in observed speech, including the position of the lips, jaw, and tongue in producing a particular phoneme.”learn.microsoft.com/en-us/azure/ai-services/speech-service/text-to-speech“Real-time speech synthesis: Use the Speech SDK or REST API to convert text to speech by using standard voices or custom voices. Asynchronous synthesis of long audio: Use the batch synthesis API to asynchronously synthesize text to speech files longer than 10 minutes”

Regions

Australia East, Brazil South, Canada Central, Canada East, Central US, East Asia, East US, East US 2, France Central, Germany West Central, India Central, Italy North, Japan East, Japan West, Korea Central, North Central US, North Europe, Norway East, Qatar Central, South Africa North, South Central US, Southeast Asia, Sweden Central, Switzerland North, Switzerland West, UAE North, UK South, UK West, West Central US, West Europe, West US, West US 2, West US 3, US Gov Arizona, US Gov Virginia [7]learn.microsoft.com/en-us/azure/ai-services/speech-service/rest-text-to-speech“These regions are supported for text to speech through the REST API: Australia East, Brazil South, Canada Central, Canada East, Central US, East Asia, East US, East US 2, France Central, Germany West Central, India Central, Italy North, Japan East, Japan West, Korea Central, North Central US, North Europe, Norway East, Qatar Central, South Africa North, South Central US, Southeast Asia, Sweden Central, Switzerland North, Switzerland West, UAE North, UK South, UK West, US Gov Arizona, US Gov Virginia, West Central US, West Europe, West US, West US 2, West US 3”

Languages

af-ZA (Afrikaans, South Africa), am-ET (Amharic, Ethiopia), ar-AE (Arabic, UAE), ar-BH (Arabic, Bahrain), ar-DZ (Arabic, Algeria), ar-EG (Arabic, Egypt), ar-IQ (Arabic, Iraq), ar-JO (Arabic, Jordan), ar-KW (Arabic, Kuwait), ar-LB (Arabic, Lebanon), ar-LY (Arabic, Libya), ar-MA (Arabic, Morocco), ar-OM (Arabic, Oman), ar-QA (Arabic, Qatar), ar-SA (Arabic, Saudi Arabia), ar-SY (Arabic, Syria), ar-TN (Arabic, Tunisia), ar-YE (Arabic, Yemen), as-IN (Assamese, India), az-AZ (Azerbaijani, Azerbaijan), bg-BG (Bulgarian, Bulgaria), bn-BD (Bangla, Bangladesh), bn-IN (Bengali, India), bs-BA (Bosnian, Bosnia and Herzegovina), ca-ES (Catalan), cs-CZ (Czech, Czechia), cy-GB (Welsh, United Kingdom), da-DK (Danish, Denmark), de-AT (German, Austria), de-CH (German, Switzerland), de-DE (German, Germany), el-GR (Greek, Greece), en-AU (English, Australia), en-CA (English, Canada), en-GB (English, United Kingdom), en-HK (English, Hong Kong SAR), en-IE (English, Ireland), en-IN (English, India), en-KE (English, Kenya), en-NG (English, Nigeria), en-NZ (English, New Zealand), en-PH (English, Philippines), en-SG (English, Singapore), en-TZ (English, Tanzania), en-US (English, United States), en-ZA (English, South Africa), es-AR (Spanish, Argentina), es-BO (Spanish, Bolivia), es-CL (Spanish, Chile), es-CO (Spanish, Colombia), es-CR (Spanish, Costa Rica), es-CU (Spanish, Cuba), es-DO (Spanish, Dominican Republic), es-EC (Spanish, Ecuador), es-ES (Spanish, Spain), es-GQ (Spanish, Equatorial Guinea), es-GT (Spanish, Guatemala), es-HN (Spanish, Honduras), es-MX (Spanish, Mexico), es-NI (Spanish, Nicaragua), es-PA (Spanish, Panama), es-PE (Spanish, Peru), es-PR (Spanish, Puerto Rico), es-PY (Spanish, Paraguay), es-SV (Spanish, El Salvador), es-US (Spanish, United States), es-UY (Spanish, Uruguay), es-VE (Spanish, Venezuela), et-EE (Estonian, Estonia), eu-ES (Basque), fa-IR (Persian, Iran), fi-FI (Finnish, Finland), fil-PH (Filipino, Philippines), fr-BE (French, Belgium), fr-CA (French, Canada), fr-CH (French, Switzerland), fr-FR (French, France), ga-IE (Irish, Ireland), gl-ES (Galician), gu-IN (Gujarati, India), he-IL (Hebrew, Israel), hi-IN (Hindi, India), hr-HR (Croatian, Croatia), hu-HU (Hungarian, Hungary), hy-AM (Armenian, Armenia), id-ID (Indonesian, Indonesia), is-IS (Icelandic, Iceland), it-IT (Italian, Italy), iu-CANS-CA (Inuktitut Syllabics, Canada), iu-LATN-CA (Inuktitut Latin, Canada), ja-JP (Japanese, Japan), jv-ID (Javanese, Indonesia), ka-GE (Georgian, Georgia), kk-KZ (Kazakh, Kazakhstan), km-KH (Khmer, Cambodia), kn-IN (Kannada, India), ko-KR (Korean, Korea), lo-LA (Lao, Laos), lt-LT (Lithuanian, Lithuania), lv-LV (Latvian, Latvia), mk-MK (Macedonian, North Macedonia), ml-IN (Malayalam, India), mn-MN (Mongolian, Mongolia), mr-IN (Marathi, India), ms-MY (Malay, Malaysia), mt-MT (Maltese, Malta), my-MM (Burmese, Myanmar), nb-NO (Norwegian Bokmål, Norway), ne-NP (Nepali, Nepal), nl-BE (Dutch, Belgium), nl-NL (Dutch, Netherlands), or-IN (Odia, India), pa-IN (Punjabi, India), pl-PL (Polish, Poland), ps-AF (Pashto, Afghanistan), pt-BR (Portuguese, Brazil), pt-PT (Portuguese, Portugal), ro-RO (Romanian, Romania), ru-RU (Russian, Russia), si-LK (Sinhala, Sri Lanka), sk-SK (Slovak, Slovakia), sl-SI (Slovenian, Slovenia), so-SO (Somali, Somalia), sq-AL (Albanian, Albania), sr-LATN-RS (Serbian Latin, Serbia), sr-RS (Serbian Cyrillic, Serbia), su-ID (Sundanese, Indonesia), sv-SE (Swedish, Sweden), sw-KE (Kiswahili, Kenya), sw-TZ (Kiswahili, Tanzania), ta-IN (Tamil, India), ta-LK (Tamil, Sri Lanka), ta-MY (Tamil, Malaysia), ta-SG (Tamil, Singapore), te-IN (Telugu, India), th-TH (Thai, Thailand), tr-TR (Turkish, Türkiye), uk-UA (Ukrainian, Ukraine), ur-IN (Urdu, India), ur-PK (Urdu, Pakistan), uz-UZ (Uzbek, Uzbekistan), vi-VN (Vietnamese, Vietnam), wuu-CN (Chinese Wu, Simplified), yue-CN (Chinese Cantonese, Simplified), zh-CN (Chinese Mandarin, Simplified), zh-HK (Chinese Cantonese, Traditional), zh-TW (Chinese Taiwanese Mandarin, Traditional) [8]learn.microsoft.com/en-us/azure/ai-services/speech-service/text-to-speech“Standard voices: High-quality neural voices available out of the box in 100+ languages and locales”learn.microsoft.com/en-us/azure/ai-services/speech-service/language-support“The text-to-speech section contains an extensive table listing supported locales including af-ZA, am-ET, ar-AE through zh-TW — approximately 140+ language-locale combinations representing over 130 distinct languages.”

Input types

plain text, SSML (Speech Synthesis Markup Language)

Output types

mp3 (various bitrates), opus (ogg, webm containers), pcm (raw), wav (riff), alaw, mulaw, truesilk, g722, amr-wb [9]learn.microsoft.com/en-us/azure/ai-services/speech-service/rest-text-to-speech“audio-16khz-32kbitrate-mono-mp3 audio-24khz-48kbitrate-mono-mp3 ogg-16khz-16bit-mono-opus webm-24khz-16bit-mono-opus raw-8khz-8bit-mono-alaw raw-8khz-8bit-mono-mulaw riff-24khz-16bit-mono-pcm g722-16khz-64kbps amr-wb-16000hz”

Webhooks

✗ No [10]learn.microsoft.com/en-us/azure/ai-services/speech-service/text-to-speech“Asynchronous synthesis of long audio: Use the batch synthesis API to asynchronously synthesize text to speech files longer than 10 minutes; responses are polled for, and synthesized audio is downloaded when the service makes it available.”

Sandbox / test mode

✗ No

SDK languages

Python, C#, JavaScript, Java, Go [11]learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-sdk“The Speech SDK supports the following languages and platforms: C#, C++, Go, Java, JavaScript, Objective-C, Python, Swift”

MCP server

✓ Yes [12]learn.microsoft.com/en-us/azure/developer/azure-mcp-server/services/azure-mcp-speech-foundry-tools“Azure Model Context Protocol (MCP) Server enables AI assistants like GitHub Copilot, Claude Desktop, and others to interact with Azure Speech in Foundry Tools through natural language commands.”

SOC 2

SOC 2 Type II [13]azure.microsoft.com/en-us/blog/cognitive-services-certifications-and-availability/“Azure Cognitive Services include ISO 27001:2013 certification, HIPAA BAA, HITRUST CSF certification, SOC 1 Type 2, SOC 2 Type 2, and SOC 3 attestation.”

HIPAA

✓ Yes [14]learn.microsoft.com/en-us/azure/compliance/offerings/offering-hipaa-us“Microsoft will enter into BAAs with its covered entity and business associate customers. Azure has enabled the physical, technical, and administrative safeguards required by HIPAA and the HITECH Act inside the in-scope Azure services, and offers a HIPAA BAA as part of the Microsoft Product Terms to all customers who are covered entities or business associates under HIPAA”

GDPR

✓ Yes [15]learn.microsoft.com/en-us/azure/foundry/responsible-ai/speech-service/text-to-speech/data-privacy-security“The Microsoft Products and Services Data Protection Addendum sets forth customers' and Microsoft's obligations with respect to the processing and security of Customer Data and Personal Data in connection with Azure”

ISO 27001

✓ Yes [16]learn.microsoft.com/en-us/azure/compliance/offerings/offering-iso-27001“Microsoft Azure, Dynamics 365, and other Microsoft online services undergo regular independent third-party audits for ISO/IEC 27001 compliance.”

PCI DSS

✓ Yes [17]learn.microsoft.com/en-us/azure/compliance/offerings/offering-pci-dss“Microsoft Azure maintains a PCI DSS validation using an approved Qualified Security Assessor (QSA), and is certified as compliant under PCI DSS version 4.0 at Service Provider Level 1.”learn.microsoft.com/en-us/azure/compliance/offerings/offering-pci-dss“For a list of Microsoft online services in audit scope, see the PCI DSS Attestation of Compliance (AoC) that is available separately for Azure and Azure Government”

Published SLA

✓ Yes [18]azure.microsoft.com/en-us/support/legal/sla/cognitive-services/v1_0/

Rate limits

Free (F0): 20 transactions per 60 seconds (not adjustable). Standard (S0): 200 transactions per second (TPS) default, adjustable up to 1,000 TPS upon request. Maximum audio length per request: 10 minutes. Maximum SSML message size per WebSocket turn: 64 KB. Maximum distinct voice/audio tags in SSML: 50. HD voice latency: less than 300 ms. [19]learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-services-quotas-and-limits“Maximum number of transactions per time period for standard voices and custom voices: Free (F0): 20 transactions per 60 seconds (This limit isn't adjustable). Standard (S0): 200 transactions per second (TPS) (default value). The rate is adjustable up to 1,000 TPS for Standard (S0) resources.”learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-services-quotas-and-limits“Maximum audio length produced per request: 10 minutes (both F0 and S0). Maximum SSML message size per turn for WebSocket: 64 KB. Maximum total number of distinct voice and audio tags in SSML: 50.”

Known restrictions

Custom voice (professional voice fine-tuning) requires limited-access application approval, Chinese characters counted as two characters for billing, including kanji (Japanese), hanja (Korean), hanzi (other languages), HD voices support only a subset of SSML elements (not full SSML), Personal voice does not support BYOS (Bring Your Own Storage), Dragon HD Flash voices only support zh-CN and en-US text, Real-time HD voice synthesis only (no batch synthesis for HD voices), Maximum 10 minutes audio output per real-time synthesis request, Custom voice endpoint hosting billed separately per hour, Voice talent verbal consent recording required before custom voice training [20]learn.microsoft.com/en-us/azure/ai-services/speech-service/text-to-speech“Custom voice is an umbrella term that includes professional voice fine-tuning and personal voice. Custom voice training and hosting are both calculated by hour and billed per second.”learn.microsoft.com/en-us/azure/ai-services/speech-service/text-to-speech“Each Chinese character is counted as two characters for billing, including kanji used in Japanese, hanja used in Korean, or hanzi used in other languages.”

• Docs
• llms.txt

Docs rendering: static · llms.txt present

API style

rest

Base URL

https://{region}.tts.speech.microsoft.com/cognitiveservices/v1

Version

2024-04-01

Versioning

url

Stability

ga

Auth methods

api_key, jwt

Error format

vendor-specific

Rate limit

200 / second

SDKs

• Python azure-cognitiveservices-speech · repo
• C# Microsoft.CognitiveServices.Speech · repo
• JavaScript microsoft-cognitiveservices-speech-sdk · repo
• Java com.microsoft.cognitiveservices.speech:client-sdk · repo
• Go github.com/Microsoft/cognitive-services-speech-sdk-go · repo

• Auth docs
• Quickstart
• MCP server

Launched

2018-09-24

GA

2018-11-01

• ElevenLabs Text to Speech

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

  Hybrid · 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)

  "Transform text into lifelike spoken audio" - OpenAI's TTS service enabling blog narration, multilingual audio production, and realtime voice output via gpt-4o-mini-tts, tts-1, and tts-1-hd models.

  Usage · public pricing · self-serve

Azure AI Text to Speech alternatives · Azure AI 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: learn.microsoft.com
2. ↑Pricing model: azure.microsoft.com · learn.microsoft.com
3. ↑Published pricing: azure.microsoft.com
4. ↑Free tier: speechify.com · learn.microsoft.com
5. ↑Enterprise plan: learn.microsoft.com
6. ↑Supported actions: learn.microsoft.com · learn.microsoft.com
7. ↑Regions: learn.microsoft.com
8. ↑Languages: learn.microsoft.com · learn.microsoft.com
9. ↑Output types: learn.microsoft.com
10. ↑Webhooks: learn.microsoft.com
11. ↑SDK languages: learn.microsoft.com
12. ↑MCP server: learn.microsoft.com
13. ↑SOC 2: azure.microsoft.com
14. ↑HIPAA: learn.microsoft.com
15. ↑GDPR: learn.microsoft.com
16. ↑ISO 27001: learn.microsoft.com
17. ↑PCI DSS: learn.microsoft.com · learn.microsoft.com
18. ↑Published SLA: azure.microsoft.com
19. ↑Rate limits: learn.microsoft.com · learn.microsoft.com
20. ↑Known restrictions: learn.microsoft.com · learn.microsoft.com

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

1. 2026-06-21 Capabilities: {} → {"ssml":true,"streaming":true,"multilingual":true,"voice_design":true,"voice_cl…
2. 2026-06-21 Summary Md: (none) → Azure AI Text to Speech is Microsoft's managed speech synthesis service, suited…
3. 2026-06-21 Score Docs Quality: (none) → 25
4. 2026-06-21 Score Procurement Friction: (none) → 100
5. 2026-06-21 Score Trust Readiness: (none) → 100
6. 2026-06-21 Best For: (none) → Prototypes and side projects - free to start, no sales call, Regulated or enter…
7. 2026-06-21 Scoring Methodology: (none) → Scores are computed deterministically from this profile's published, sourced fi…
8. 2026-06-21 Score Agent Friendliness: (none) → 65
9. 2026-06-21 Score Pricing Transparency: (none) → 100
10. 2026-06-21 Score Setup Speed: (none) → 85
11. 2026-06-21 Llms Txt Present: (none) → Yes
12. 2026-06-21 Rendering: (none) → static
13. 2026-06-21 Has Structured Data: (none) → Yes
14. 2026-06-21 Robots Allows Agents: (none) → Yes
15. 2026-06-21 Docs URL: (none) → https://azure.microsoft.com/en-us/resources/developers/
16. 2026-06-21 Llms Txt URL: (none) → https://azure.microsoft.com/llms.txt
17. 2026-06-21 Pricing Model: set to usage_based
18. 2026-06-21 Has Published Pricing: set to Yes
19. 2026-06-21 Free Tier Available: set to Yes
20. 2026-06-21 Free Tier Details: set to Free (F0) tier: 0.5 million characters per month for neural text-to-speech (rec…
21. 2026-06-21 Self Serve Signup: set to Yes
22. 2026-06-21 Requires Sales Call: set to No
23. 2026-06-21 Enterprise Plan Available: set to Yes
24. 2026-06-21 SOC 2: set to type_2
25. 2026-06-21 HIPAA: set to Yes
26. 2026-06-21 GDPR: set to Yes
27. 2026-06-21 ISO 27001: set to Yes
28. 2026-06-21 PCI DSS: set to Yes
29. 2026-06-21 SLA Published: set to Yes
30. 2026-06-21 SLA URL: set to https://www.microsoft.com/licensing/docs/view/Service-Level-Agreements-SLA-for-…
31. 2026-06-21 Data Retention Policy URL: set to https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/speech-service/t…
32. 2026-06-21 Documented Rate Limits: set to Free (F0): 20 transactions per 60 seconds (not adjustable). Standard (S0): 200 …
33. 2026-06-21 Rate Limit Requests: set to 200
34. 2026-06-21 Rate Limit Window: set to second
35. 2026-06-21 Known Restrictions: set to Custom voice (professional voice fine-tuning) requires limited-access applicati…
36. 2026-06-21 Auth Methods: set to api_key, jwt
37. 2026-06-21 Auth Docs URL: set to https://learn.microsoft.com/en-us/azure/ai-services/speech-service/rest-text-to…
38. 2026-06-21 API Style: set to rest
39. 2026-06-21 Base URL: set to https://{region}.tts.speech.microsoft.com/cognitiveservices/v1
40. 2026-06-21 API Version: set to 2024-04-01
41. 2026-06-21 Versioning Scheme: set to url
42. 2026-06-21 Stability: set to ga
43. 2026-06-21 MCP URL: set to https://github.com/microsoft/mcp/tree/main/servers/Azure.Mcp.Server
44. 2026-06-21 Quickstart URL: set to https://learn.microsoft.com/en-us/azure/ai-services/speech-service/get-started-…
45. 2026-06-21 Error Format: set to vendor-specific
46. 2026-06-21 Slug: set to azure-text-to-speech
47. 2026-06-21 Starting Price Usd: set to 15
48. 2026-06-21 Price Basis: set to 1M characters
49. 2026-06-21 Free Tier Limit: set to 500,000 characters/month
50. 2026-06-21 Launched At: set to 2018-09-24

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

curl -X POST https://apio.sh/api/suggest/azure-text-to-speech/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 →