Amazon Polly

Best for: Prototypes and side projects - free to start, no sales call; Teams needing broad API coverage out of the box; Cost-sensitive teams - low, transparent entry price

Pricing model

Usage-based [2]aws.amazon.com/polly/pricing/“You are billed monthly for the number of characters of text that you processed.”

Published pricing

✓ Yes [3]aws.amazon.com/polly/pricing/“Standard voices: $4.00 per 1 million characters. Neural voices: $16.00 per 1 million characters. Long-Form voices: $100.00 per 1 million characters. Generative voices: $30.00 per 1 million characters.”

Free tier

✓ Yes [4]aws.amazon.com/polly/pricing/“Standard voices: 5 million characters per month for speech or Speech Marks requests”aws.amazon.com/polly/pricing/“Neural voices: 1 million characters per month for speech or Speech Marks requests, for the first 12 months”

Free tier details

Standard voices: 5 million characters/month (permanent, always-free). Neural voices: 1 million characters/month for the first 12 months. Long-Form voices: 500 thousand characters/month for the first 12 months. Generative voices: 100 thousand characters/month for the first 12 months. [5]aws.amazon.com/polly/pricing/“Standard voices: 5 million characters per month for speech or Speech Marks requests ... Neural voices: 1 million characters per month for speech or Speech Marks requests, for the first 12 months ... Long-Form voices: 500 thousand characters per month ... for the first 12 months ... Generative voices: 100 thousand characters per month for speech requests, for the first 12 months”

Self-serve signup

✓ Yes

Requires sales call

✗ No

Enterprise plan

✗ No

• Real-time streaming
• SSML control
• Multilingual voices
• Word timestamps

Supported actions

synthesize_speech, streaming_tts, async_synthesis_task, ssml_support, custom_lexicons, speech_marks, word_timestamps, sentence_timestamps, viseme_timestamps, newscaster_speaking_style, neural_tts, standard_tts, long_form_tts, generative_tts, describe_voices, put_lexicon, get_lexicon, list_lexicons, delete_lexicon, get_speech_synthesis_task, list_speech_synthesis_tasks, start_speech_synthesis_stream [6]docs.aws.amazon.com/polly/latest/dg/API_Operations.html“The following actions are supported: DeleteLexicon, DescribeVoices, GetLexicon, GetSpeechSynthesisTask, ListLexicons, ListSpeechSynthesisTasks, PutLexicon, StartSpeechSynthesisStream, StartSpeechSynthesisTask, SynthesizeSpeech”docs.aws.amazon.com/polly/latest/dg/API_SynthesizeSpeech.html“Synthesizes UTF-8 input, plain text or SSML, to a stream of bytes.”

Regions

US East (Ohio), US East (N. Virginia), US West (N. California), US West (Oregon), Africa (Cape Town), Asia Pacific (Hong Kong), Asia Pacific (Malaysia), Asia Pacific (Mumbai), Asia Pacific (Osaka), Asia Pacific (Seoul), Asia Pacific (Singapore), Asia Pacific (Sydney), Asia Pacific (Thailand), Asia Pacific (Tokyo), Canada (Central), Europe (Frankfurt), Europe (Ireland), Europe (London), Europe (Paris), Europe (Spain), Europe (Stockholm), Europe (Zurich), Middle East (Bahrain), South America (São Paulo), AWS GovCloud (US-West) [7]docs.aws.amazon.com/general/latest/gr/pol.html“US East (Ohio), US East (N. Virginia), US West (N. California), US West (Oregon), Africa (Cape Town), Asia Pacific (Hong Kong)...”

Languages

Arabic (arb), Arabic Gulf (ar-AE), Catalan (ca-ES), Chinese Cantonese (yue-CN), Chinese Mandarin (cmn-CN), Czech (cs-CZ), Danish (da-DK), Dutch Belgian (nl-BE), Dutch (nl-NL), English Australian (en-AU), English British (en-GB), English Indian (en-IN), English New Zealand (en-NZ), English Singaporean (en-SG), English South African (en-ZA), English US (en-US), English Welsh (en-GB-WLS), Finnish (fi-FI), French (fr-FR), French Belgian (fr-BE), French Canadian (fr-CA), Hindi (hi-IN), German (de-DE), German Austrian (de-AT), German Swiss (de-CH), Icelandic (is-IS), Italian (it-IT), Japanese (ja-JP), Korean (ko-KR), Norwegian (nb-NO), Polish (pl-PL), Portuguese Brazilian (pt-BR), Portuguese European (pt-PT), Romanian (ro-RO), Russian (ru-RU), Spanish Spain (es-ES), Spanish Mexican (es-MX), Spanish US (es-US), Swedish (sv-SE), Turkish (tr-TR), Welsh (cy-GB) [8]docs.aws.amazon.com/polly/latest/dg/supported-languages.html“The following languages are supported by Amazon Polly and can be used to synthesize speech. Each language has a unique language code.”

Input types

plain text, SSML

Output types

mp3, ogg_vorbis, ogg_opus, pcm, mulaw, alaw, json (speech marks) [9]docs.aws.amazon.com/polly/latest/dg/API_SynthesizeSpeech.html“The format in which the returned output will be encoded. For audio stream, this will be mp3, ogg_vorbis, ogg_opus, mu-law, a-law or pcm. For speech marks, this will be json. Valid Values: json | mp3 | ogg_opus | ogg_vorbis | pcm | mulaw | alaw”

Webhooks

✗ No [10]docs.aws.amazon.com/polly/latest/dg/API_Operations.html“The following actions are supported: DeleteLexicon, DescribeVoices, GetLexicon, GetSpeechSynthesisTask, ListLexicons, ListSpeechSynthesisTasks, PutLexicon, StartSpeechSynthesisStream, StartSpeechSynthesisTask, SynthesizeSpeech”

Sandbox / test mode

✗ No [11]aws.amazon.com/polly/pricing/“You are billed monthly for the number of characters of text that you processed.”

SDK languages

Python, Node.js, Java, Go, C++, .NET, Ruby, PHP, Rust, Kotlin [12]docs.aws.amazon.com/polly/latest/dg/sdk-general-information-section.html“AWS SDK for C++, AWS CLI, AWS SDK for Go, AWS SDK for Java, AWS SDK for JavaScript, AWS SDK for Kotlin, AWS SDK for .NET, AWS SDK for PHP, AWS Tools for PowerShell, AWS SDK for Python (Boto3), AWS SDK for Ruby, AWS SDK for Rust, AWS SDK for SAP ABAP, AWS SDK for Swift”

MCP server

✗ No [13]aws.amazon.com/polly/“Amazon Polly is a fully-managed service that generates voice on demand, converting any text to an audio stream.”

SOC 2

SOC 2 Type II [14]docs.aws.amazon.com/polly/latest/dg/AMAZON-POLLY-compliance.html“Third-party auditors assess the security and compliance of Amazon Polly as part of multiple AWS compliance programs. These include SOC, PCI, FedRAMP, HIPAA, and others.”aws.amazon.com/compliance/services-in-scope/SOC/“Amazon Polly appears in the service list with a checkmark (✓) indicating it is currently in scope and is reflected in current reports for SOC 1, 2, and 3 compliance programs.”

HIPAA

✓ Yes [15]aws.amazon.com/compliance/hipaa-eligible-services-reference/“Amazon Polly is listed as a HIPAA eligible service.”docs.aws.amazon.com/polly/latest/dg/what-is.html“Amazon Polly is certified for use with regulated workloads for HIPAA (the Health Insurance Portability and Accountability Act of 1996), and Payment Card Industry Data Security Standard (PCI DSS).”

GDPR

✓ Yes [16]aws.amazon.com/compliance/gdpr-center/“AWS customers can use all AWS services to process personal data (as defined in the GDPR) that is uploaded to the AWS services under their AWS accounts (customer data) in compliance with the GDPR.”aws.amazon.com/compliance/gdpr-center/“all AWS services are GDPR ready”

ISO 27001

✓ Yes [17]aws.amazon.com/compliance/iso-certified/“Amazon Polly appears in the comprehensive list of AWS services covered under ISO/IEC 27001:2022 certification.”

PCI DSS

✓ Yes [18]aws.amazon.com/compliance/services-in-scope/PCI/“Amazon Polly is listed as in scope for PCI DSS compliance.”docs.aws.amazon.com/polly/latest/dg/what-is.html“Amazon Polly is certified for use with regulated workloads for HIPAA (the Health Insurance Portability and Accountability Act of 1996), and Payment Card Industry Data Security Standard (PCI DSS).”

Published SLA

✓ Yes [19]aws.amazon.com/machine-learning/language/sla/“Amazon Comprehend, Amazon Comprehend Medical, Amazon Lex, Amazon Polly, Amazon Transcribe, Amazon Transcribe Medical, AWS HealthScribe, Amazon Translate”

Rate limits

SynthesizeSpeech (standard): 80 requests/sec; SynthesizeSpeech (neural/long-form/generative): 8 requests/sec; StartSpeechSynthesisTask (standard/neural): 10 requests/sec; StartSpeechSynthesisTask (generative/long-form): 1 request/sec. SynthesizeSpeech max input: 6,000 total characters / 3,000 billed characters per request. StartSpeechSynthesisTask max input: 200,000 total characters / 100,000 billed characters per request. All limits are per region and adjustable via Service Quotas. [20]docs.aws.amazon.com/general/latest/gr/pol.html“Default SynthesizeSpeech billed character count: Each supported Region: 3,000 ... Default SynthesizeSpeech total character count: Each supported Region: 6,000”docs.aws.amazon.com/general/latest/gr/pol.html“Default rate of SynthesizeSpeech (standard) requests: Each supported Region: 80 ... Default rate of SynthesizeSpeech (neural) requests: Each supported Region: 8 ... Default rate of SynthesizeSpeech (generative) requests: Each supported Region: 8”

Known restrictions

SynthesizeSpeech API: maximum 6,000 total characters (including SSML tags) or 3,000 billed characters per request, StartSpeechSynthesisTask API: maximum 200,000 total characters or 100,000 billed characters per request, Maximum 5 lexicons per synthesis request, Maximum 100 lexicons per account per region, Maximum lexicon size: 40,000 characters, Speech marks (JSON) cannot be combined with audio output formats in a single request, Not all voices support all engines (standard/neural/long-form/generative), Not all alphabets/scripts are available for all voices [21]docs.aws.amazon.com/general/latest/gr/pol.html“Default SynthesizeSpeech lexicon count: Each supported Region: 5 ... Default lexicon count: Each supported Region: 100”docs.aws.amazon.com/polly/latest/dg/API_SynthesizeSpeech.html“The value of the "Text" parameter is longer than the accepted limits. For the SynthesizeSpeech API, the limit for input text is a maximum of 6000 characters total, of which no more than 3000 can be billed characters.”

• Docs
• Status page

Docs rendering: static

API style

rest

Base URL

https://polly.{region}.amazonaws.com

Version

2016-06-10

Versioning

url

Stability

ga

Auth methods

hmac_signature

Error format

vendor-specific

Rate limit

80 / second

SDKs

• Python boto3 · repo
• Node.js @aws-sdk/client-polly · repo
• Java software.amazon.awssdk:polly · repo
• Go github.com/aws/aws-sdk-go-v2/service/polly · repo
• C++ aws-sdk-cpp (polly) · repo
• .NET AWSSDK.Polly · repo
• Ruby aws-sdk-polly · repo
• PHP aws/aws-sdk-php · repo
• Rust aws-sdk-polly · repo
• Kotlin aws.sdk.kotlin:polly · repo

• Auth docs
• Quickstart
• Deprecation policy

Launched

2016-11-30

GA

2016-11-30

• 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

• 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

Amazon Polly alternatives · Amazon Polly 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: docs.aws.amazon.com
2. ↑Pricing model: aws.amazon.com
3. ↑Published pricing: aws.amazon.com
4. ↑Free tier: aws.amazon.com · aws.amazon.com
5. ↑Free tier details: aws.amazon.com
6. ↑Supported actions: docs.aws.amazon.com · docs.aws.amazon.com
7. ↑Regions: docs.aws.amazon.com
8. ↑Languages: docs.aws.amazon.com
9. ↑Output types: docs.aws.amazon.com
10. ↑Webhooks: docs.aws.amazon.com
11. ↑Sandbox: aws.amazon.com
12. ↑SDK languages: docs.aws.amazon.com
13. ↑MCP server: aws.amazon.com
14. ↑SOC 2: docs.aws.amazon.com · aws.amazon.com
15. ↑HIPAA: aws.amazon.com · docs.aws.amazon.com
16. ↑GDPR: aws.amazon.com · aws.amazon.com
17. ↑ISO 27001: aws.amazon.com
18. ↑PCI DSS: aws.amazon.com · docs.aws.amazon.com
19. ↑Published SLA: aws.amazon.com
20. ↑Rate limits: docs.aws.amazon.com · docs.aws.amazon.com
21. ↑Known restrictions: docs.aws.amazon.com · docs.aws.amazon.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,"word_timestamps":true}
2. 2026-06-21 Summary Md: (none) → Amazon Polly is an AWS cloud text-to-speech service, launched in 2016, suited f…
3. 2026-06-21 Score Pricing Transparency: (none) → 100
4. 2026-06-21 Score Setup Speed: (none) → 85
5. 2026-06-21 Score Docs Quality: (none) → 15
6. 2026-06-21 Score Procurement Friction: (none) → 100
7. 2026-06-21 Score Trust Readiness: (none) → 100
8. 2026-06-21 Best For: (none) → Prototypes and side projects - free to start, no sales call, Teams needing broa…
9. 2026-06-21 Scoring Methodology: (none) → Scores are computed deterministically from this profile's published, sourced fi…
10. 2026-06-21 Score Agent Friendliness: (none) → 30
11. 2026-06-21 Robots Allows Agents: (none) → Yes
12. 2026-06-21 Status Page URL: (none) → https://status.aws.amazon.com
13. 2026-06-21 Docs URL: (none) → https://docs.aws.amazon.com/
14. 2026-06-21 Has Structured Data: (none) → Yes
15. 2026-06-21 Rendering: (none) → static
16. 2026-06-21 Llms Txt Present: (none) → No
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 Standard voices: 5 million characters/month (permanent, always-free). Neural vo…
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 No
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://aws.amazon.com/ai/services/language-sla/
31. 2026-06-21 Data Retention Policy URL: set to https://docs.aws.amazon.com/polly/latest/dg/data-protection.html
32. 2026-06-21 Documented Rate Limits: set to SynthesizeSpeech (standard): 80 requests/sec; SynthesizeSpeech (neural/long-for…
33. 2026-06-21 Rate Limit Requests: set to 80
34. 2026-06-21 Rate Limit Window: set to second
35. 2026-06-21 Known Restrictions: set to SynthesizeSpeech API: maximum 6,000 total characters (including SSML tags) or 3…
36. 2026-06-21 Auth Methods: set to hmac_signature
37. 2026-06-21 Auth Docs URL: set to https://docs.aws.amazon.com/polly/latest/dg/security-iam.html
38. 2026-06-21 API Style: set to rest
39. 2026-06-21 Base URL: set to https://polly.{region}.amazonaws.com
40. 2026-06-21 API Version: set to 2016-06-10
41. 2026-06-21 Versioning Scheme: set to url
42. 2026-06-21 Stability: set to ga
43. 2026-06-21 Deprecation Policy URL: set to https://docs.aws.amazon.com/general/latest/gr/service-lifecycle.html
44. 2026-06-21 Quickstart URL: set to https://docs.aws.amazon.com/polly/latest/dg/getting-started.html
45. 2026-06-21 Error Format: set to vendor-specific
46. 2026-06-21 Slug: set to amazon-polly
47. 2026-06-21 Starting Price Usd: set to 4
48. 2026-06-21 Price Basis: set to 1M characters
49. 2026-06-21 Free Tier Limit: set to 5 million characters/month (standard voices, permanent); 1 million characters/m…
50. 2026-06-21 Launched At: set to 2016-11-30

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

curl -X POST https://apio.sh/api/suggest/amazon-polly/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 →