Amazon Transcribe

Best for: Prototypes and side projects - free to start, no sales call; Regulated or enterprise workloads - compliance attestations and an enterprise plan; Teams needing broad API coverage out of the box

Pricing model

Usage-based [2]aws.amazon.com/transcribe/pricing/“Pay-as-you-go based on audio duration transcribed monthly, billed in one-second increments with a 15-second minimum per request.”docs.aws.amazon.com/transcribe/latest/dg/what-is.html“Amazon Transcribe is a pay-as-you-go service; pricing is based on seconds of transcribed audio, billed on a monthly basis.”

Published pricing

✓ Yes [3]aws.amazon.com/transcribe/pricing/“Batch Transcription: $0.006 per minute. Streaming Transcription: $0.01 per minute.”

Free tier

✓ Yes [4]aws.amazon.com/free/machine-learning/“Amazon Transcribe: 12-month free trial. 60 minutes per month.”aws.amazon.com/transcribe/pricing/“60 minutes per month for 12 months available at signup across Amazon Transcribe, Call Analytics, and Transcribe Medical.”

Free tier details

60 minutes per month for the first 12 months after account creation, shared across Amazon Transcribe standard, Call Analytics, and Transcribe Medical. Unused minutes do not roll over. [5]aws.amazon.com/transcribe/pricing/“60 minutes per month for 12 months available at signup across Amazon Transcribe, Call Analytics, and Transcribe Medical.”

Self-serve signup

✓ Yes

Requires sales call

✗ No

Enterprise plan

✓ Yes [6]aws.amazon.com/transcribe/pricing/“For larger workloads, additional volume discounts may be available through AWS pricing specialists.”

• Real-time streaming
• Speaker diarization
• Medical transcription
• PII redaction

Supported actions

transcribe_batch, transcribe_streaming, speaker_diarization, language_detection, multi_language_identification, word_timestamps, confidence_scores, custom_vocabulary, custom_language_models, vocabulary_filtering, automatic_punctuation, channel_identification, pii_redaction, pii_identification, subtitles_generation, alternative_transcriptions, call_analytics_batch, call_analytics_streaming, sentiment_analysis, call_summarization, issue_detection, call_categorization, medical_transcription, phi_identification, job_queueing, content_redaction_audio [7]docs.aws.amazon.com/transcribe/latest/dg/feature-matrix.html“Feature comparison: Alternative transcriptions, Channel identification, Job queueing, Language identification, Multi-language identification, Speaker diarization, Custom language models, Custom vocabularies, Redacting transcripts, Vocabulary filtering, Subtitles, Call summarization, Speaker sentiment, Real-time issue detection.”

Regions

US East (N. Virginia) us-east-1, US East (Ohio) us-east-2, US West (N. California) us-west-1, US West (Oregon) us-west-2, Africa (Cape Town) af-south-1, Asia Pacific (Hong Kong) ap-east-1, Asia Pacific (Mumbai) ap-south-1, Asia Pacific (Seoul) ap-northeast-2, Asia Pacific (Singapore) ap-southeast-1, Asia Pacific (Sydney) ap-southeast-2, Asia Pacific (Tokyo) ap-northeast-1, Asia Pacific (Malaysia) ap-southeast-5, Asia Pacific (Thailand) ap-southeast-7, Canada (Central) ca-central-1, Europe (Frankfurt) eu-central-1, Europe (Ireland) eu-west-1, Europe (London) eu-west-2, Europe (Paris) eu-west-3, Europe (Stockholm) eu-north-1, Europe (Zurich) eu-central-2, Middle East (Bahrain) me-south-1, Mexico (Central) mx-central-1, South America (São Paulo) sa-east-1, AWS GovCloud (US-East) us-gov-east-1, AWS GovCloud (US-West) us-gov-west-1 [8]docs.aws.amazon.com/transcribe/latest/dg/what-is.html“Amazon Transcribe is supported in the following AWS Regions: af-south-1 (Cape Town), ap-east-1 (Hong Kong), ap-northeast-1 (Tokyo), ap-northeast-2 (Seoul), ap-south-1 (Mumbai), ap-southeast-1 (Singapore), ap-southeast-2 (Sydney), ap-southeast-5 (Malaysia), ap-southeast-7 (Thailand), ca-central-1 (Canada, Central), eu-central-1 (Frankfurt), eu-central-2 (Zurich), eu-north-1 (Stockholm), eu-west-1 (Ireland), eu-west-2 (London), eu-west-3 (Paris), me-south-1 (Bahrain), mx-central-1 (Mexico), sa-east-1 (São Paulo), us-east-1, us-east-2, us-gov-east-1, us-gov-west-1, us-west-1, us-west-2.”

Languages

Abkhaz (ab-GE), Afrikaans (af-ZA), Albanian (sq-AL), Amharic (am-ET), Arabic Gulf (ar-AE), Arabic Modern Standard (ar-SA), Armenian (hy-AM), Asturian (ast-ES), Azerbaijani (az-AZ), Bashkir (ba-RU), Basque (eu-ES), Belarusian (be-BY), Bengali (bn-IN), Bosnian (bs-BA), Bulgarian (bg-BG), Burmese (my-MM), Catalan (ca-ES), Central Kurdish Iran (ckb-IR), Central Kurdish Iraq (ckb-IQ), Chinese Cantonese (zh-HK), Chinese Simplified (zh-CN), Chinese Traditional (zh-TW), Croatian (hr-HR), Czech (cs-CZ), Danish (da-DK), Dutch (nl-NL), English Australian (en-AU), English British (en-GB), English Indian (en-IN), English Irish (en-IE), English New Zealand (en-NZ), English Scottish (en-AB), English South African (en-ZA), English US (en-US), English Welsh (en-WL), Estonian (et-EE), Farsi (fa-IR), Farsi Afghan (fa-AF), Finnish (fi-FI), French (fr-FR), French Canadian (fr-CA), Galician (gl-ES), Georgian (ka-GE), German (de-DE), German Swiss (de-CH), Greek (el-GR), Gujarati (gu-IN), Haitian Creole (ht-HT), Hausa (ha-NG), Hebrew (he-IL), Hindi Indian (hi-IN), Hungarian (hu-HU), Icelandic (is-IS), Indonesian (id-ID), Italian (it-IT), Japanese (ja-JP), Javanese (jv-ID), Kabyle (kab-DZ), Kannada (kn-IN), Kazakh (kk-KZ), Khmer (km-KH), Kinyarwanda (rw-RW), Korean (ko-KR), Kyrgyz (ky-KG), Latvian (lv-LV), Lithuanian (lt-LT), Luganda (lg-IN), Macedonian (mk-MK), Malay (ms-MY), Malayalam (ml-IN), Maltese (mt-MT), Marathi (mr-IN), Meadow Mari (mhr-RU), Mongolian (mn-MN), Nepali (ne-NP), Norwegian Bokmål (no-NO), Odia/Oriya (or-IN), Pashto (ps-AF), Polish (pl-PL), Portuguese (pt-PT), Portuguese Brazilian (pt-BR), Punjabi (pa-IN), Romanian (ro-RO), Russian (ru-RU), Serbian (sr-RS), Sinhala (si-LK), Slovak (sk-SK), Slovenian (sl-SI), Somali (so-SO), Spanish (es-ES), Spanish Mexican (es-MX), Spanish US (es-US), Sundanese (su-ID), Swahili Kenya (sw-KE), Swahili Burundi (sw-BI), Swahili Rwanda (sw-RW), Swahili Tanzania (sw-TZ), Swahili Uganda (sw-UG), Swedish (sv-SE), Tagalog/Filipino (tl-PH), Tamil (ta-IN), Tatar (tt-RU), Telugu (te-IN), Thai (th-TH), Turkish (tr-TR), Ukrainian (uk-UA), Uyghur (ug-CN), Uzbek (uz-UZ), Vietnamese (vi-VN), Welsh (cy-WL), Wolof (wo-SN), Zulu (zu-ZA) [9]docs.aws.amazon.com/transcribe/latest/dg/supported-languages.html“The languages supported by Amazon Transcribe are listed in the following table; also listed are the features that are language-specific.”

Input types

audio file via Amazon S3 (batch), media stream via HTTP/2 (streaming), media stream via WebSocket (streaming), FLAC (recommended lossless), WAV with PCM 16-bit encoding (recommended lossless), single-channel audio, dual-channel audio, sample rates 8,000 Hz to 48,000 Hz

Output types

JSON transcript with full text, word-level timestamps (start time, end time), confidence scores per word, speaker-labeled transcript (diarization), channel-identified transcript, SRT/VTT subtitles (batch), redacted transcript (PII removed), call analytics JSON with sentiment and categories

Webhooks

✗ No [10]docs.aws.amazon.com/transcribe/latest/dg/how-input.html“All batch transcripts are stored in Amazon S3 buckets. You can choose to save your transcript in your own Amazon S3 bucket, or have Amazon Transcribe use a secure default bucket.”

Sandbox / test mode

✗ No [11]docs.aws.amazon.com/transcribe/latest/dg/getting-started.html“Before you can create transcriptions, you have a few prerequisites: Sign up for an AWS account, Install the AWS CLI and SDKs, Configure IAM credentials.”

SDK languages

Python (batch), Python (streaming), JavaScript/Node.js (streaming), Java V2 (streaming), C++ (streaming), Ruby V3, PHP V3, Go [12]docs.aws.amazon.com/transcribe/latest/APIReference/Welcome.html“Python Boto3, Python Streaming SDK for Amazon Transcribe, JavaScript V3, Java V2, C++, Ruby V3, PHP V3, Go, .NET, Rust, AWS CLI”

MCP server

✗ No

SOC 2

SOC 2 Type II [13]aws.amazon.com/compliance/services-in-scope/SOC/“Amazon Transcribe — checkmark under SOC 1,2,3 column indicating it is currently in scope and reflected in current reports.”

HIPAA

✓ Yes [14]docs.aws.amazon.com/transcribe/latest/dg/what-is.html“Amazon Transcribe is covered under AWS's HIPAA eligibility and BAA which requires BAA customers to encrypt all PHI at rest and in transit when in use.”aws.amazon.com/compliance/hipaa-eligible-services-reference/“AWS Transcribe [Includes Healthscribe] — listed as HIPAA eligible service.”

GDPR

✓ Yes [15]aws.amazon.com/compliance/gdpr-center/“AWS customers can use all AWS services to process personal data (as defined in the GDPR) in compliance with the GDPR. The AWS DPA confirms that the SCCs will apply automatically whenever an AWS customer uses AWS services to transfer customer data.”

ISO 27001

✓ Yes [16]aws.amazon.com/compliance/iso-certified/“AWS has certification for compliance with ISO/IEC 27001:2022. Amazon Transcribe is included in the comprehensive list of covered services.”

PCI DSS

✓ Yes [17]aws.amazon.com/compliance/services-in-scope/PCI/“Amazon Transcribe — checkmark under PCI DSS column, indicating it is currently in scope and reflected in current reports.”

Published SLA

✓ Yes [18]aws.amazon.com/ai/services/language-sla/“Amazon Transcribe is listed among Amazon ML Language Services. Monthly Uptime Percentage tiers: 99.0–99.9% = 10% credit; 95.0–99.0% = 25% credit; Below 95.0% = 100% credit.”

Rate limits

Concurrent transcription jobs: 250 (adjustable). Concurrent streams (HTTP/2 + WebSocket): 25 (adjustable). StartTranscriptionJob: 25 TPS (adjustable). StartStreamTranscription: 25 TPS (adjustable). Maximum audio file length: 28,800 seconds (8 hours). Maximum audio file size: 2 GB. Minimum audio file duration: 500 milliseconds. Job records retained: 90 days. [19]docs.aws.amazon.com/general/latest/gr/transcribe.html“Number of concurrent transcription jobs: Each supported Region: 250 (Adjustable Yes). Number of concurrent streams (HTTP/2 + Websocket): Each supported Region: 25 (Adjustable Yes). Transactions per second, StartTranscriptionJob: Each supported Region: 25 per second. Maximum audio file length: 28,800 Seconds (No). Maximum audio file size: 2 Gigabytes (No).”

Known restrictions

Maximum audio file length: 28,800 seconds (8 hours) for standard batch, Maximum audio file size: 2 GB, Maximum audio file length for Medical batch: 14,400 seconds (4 hours), Maximum audio file length for Call Analytics batch: 14,400 seconds (4 hours), Streaming sessions limited to 4 hours per open connection, Media with more than two channels is not currently supported, Amazon Transcribe Medical is only available in US English, Automatic content redaction does not remove PII from source audio files, only transcripts, Custom language model training limited to 5 concurrent jobs and 10 models per account by default, Billing in one-second increments with a 15-second minimum per request [20]docs.aws.amazon.com/general/latest/gr/transcribe.html“Maximum audio file length: Each supported Region: 28,800 Seconds | No. Maximum audio file size: Each supported Region: 2 Gigabytes | No. Minimum audio file duration: Each supported Region: 500 Milliseconds | No.”docs.aws.amazon.com/transcribe/latest/dg/how-input.html“Amazon Transcribe supports single-channel and dual-channel media. Media with more than two channels is not currently supported.”

• Docs
• Status page

Docs rendering: static

API style

rest

Base URL

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

Versioning

none

Stability

ga

Auth methods

hmac_signature

Error format

vendor-specific

Rate limit

25 / second

SDKs

• Python (batch) boto3 · repo
• Python (streaming) amazon-transcribe · repo
• JavaScript/Node.js (streaming) @aws-sdk/client-transcribe-streaming · repo
• Java V2 (streaming) software.amazon.awssdk:transcribestreaming · repo
• C++ (streaming) aws-cpp-sdk-transcribestreaming · repo
• Ruby V3 aws-sdk-transcribestreamingservice · repo
• PHP V3 aws/aws-sdk-php · repo
• Go github.com/aws/aws-sdk-go-v2/service/transcribestreaming · repo

• Auth docs
• Quickstart

Launched

2017-11-29

GA

2018-04-04

• 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."

  Hybrid · free tier · public pricing · self-serve

• 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."

  Usage · free tier · public pricing · self-serve

• Google Cloud Speech-to-Text

  "Accurate voice typing and transcription powered by Gemini."

  Usage · free tier · public pricing · self-serve

• 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."

  Usage · free tier · public pricing · self-serve

• AssemblyAI

  "Voice AI infrastructure for developers building products that transcribe, understand, and act on speech."

  Usage · public pricing · self-serve

• Speechmatics

  "Low-latency speech-to-text for multilingual, multi-speaker conversations."

  Usage · free tier · public pricing · self-serve

Amazon Transcribe alternatives · Amazon Transcribe vs ElevenLabs Scribe (Speech to Text) · All Speech-to-Text & Transcription APIs APIs

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

1. ↑Description: docs.aws.amazon.com · aws.amazon.com
2. ↑Pricing model: aws.amazon.com · docs.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. ↑Enterprise plan: aws.amazon.com
7. ↑Supported actions: docs.aws.amazon.com
8. ↑Regions: docs.aws.amazon.com
9. ↑Languages: docs.aws.amazon.com
10. ↑Webhooks: docs.aws.amazon.com
11. ↑Sandbox: docs.aws.amazon.com
12. ↑SDK languages: docs.aws.amazon.com
13. ↑SOC 2: aws.amazon.com
14. ↑HIPAA: docs.aws.amazon.com · aws.amazon.com
15. ↑GDPR: aws.amazon.com
16. ↑ISO 27001: aws.amazon.com
17. ↑PCI DSS: aws.amazon.com
18. ↑Published SLA: aws.amazon.com
19. ↑Rate limits: docs.aws.amazon.com
20. ↑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: {} → {"medical":true,"pii_redaction":true,"real_time_streaming":true,"speaker_diariz…
2. 2026-06-21 Summary Md: (none) → Amazon Transcribe is an automatic speech recognition service from AWS that conv…
3. 2026-06-21 Score Setup Speed: (none) → 85
4. 2026-06-21 Score Pricing Transparency: (none) → 100
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, Regulated or enter…
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 Has Structured Data: (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 Llms Txt Present: (none) → No
15. 2026-06-21 Rendering: (none) → static
16. 2026-06-21 Robots Allows Agents: (none) → Yes
17. 2026-06-21 SDK Packages: set to Python (batch), Python (streaming), JavaScript/Node.js (streaming), Java V2 (st…
18. 2026-06-21 MCP Server Available: set to No
19. 2026-06-21 Pricing Model: set to usage_based
20. 2026-06-21 Has Published Pricing: set to Yes
21. 2026-06-21 Free Tier Available: set to Yes
22. 2026-06-21 Free Tier Details: set to 60 minutes per month for the first 12 months after account creation, shared acr…
23. 2026-06-21 Self Serve Signup: set to Yes
24. 2026-06-21 Requires Sales Call: set to No
25. 2026-06-21 Enterprise Plan Available: set to Yes
26. 2026-06-21 SOC 2: set to type_2
27. 2026-06-21 HIPAA: set to Yes
28. 2026-06-21 GDPR: set to Yes
29. 2026-06-21 ISO 27001: set to Yes
30. 2026-06-21 PCI DSS: set to Yes
31. 2026-06-21 SLA Published: set to Yes
32. 2026-06-21 SLA URL: set to https://aws.amazon.com/ai/services/language-sla/
33. 2026-06-21 Data Retention Policy URL: set to https://docs.aws.amazon.com/transcribe/latest/dg/opt-out.html
34. 2026-06-21 Documented Rate Limits: set to Concurrent transcription jobs: 250 (adjustable). Concurrent streams (HTTP/2 + W…
35. 2026-06-21 Rate Limit Requests: set to 25
36. 2026-06-21 Rate Limit Window: set to second
37. 2026-06-21 Auth Methods: set to hmac_signature
38. 2026-06-21 Auth Docs URL: set to https://docs.aws.amazon.com/transcribe/latest/dg/security-iam.html
39. 2026-06-21 API Style: set to rest
40. 2026-06-21 Base URL: set to https://transcribe.{region}.amazonaws.com
41. 2026-06-21 Stability: set to ga
42. 2026-06-21 Quickstart URL: set to https://docs.aws.amazon.com/transcribe/latest/dg/getting-started.html
43. 2026-06-21 Error Format: set to vendor-specific
44. 2026-06-21 Requires Verification: set to No
45. 2026-06-21 Starting Price Usd: set to 0.006
46. 2026-06-21 Price Basis: set to minute
47. 2026-06-21 Free Tier Limit: set to 60 minutes/month for 12 months
48. 2026-06-21 Launched At: set to 2017-11-29
49. 2026-06-21 GA Date: set to 2018-04-04
50. 2026-06-21 Notable Customers: set to (none)

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

curl -X POST https://apio.sh/api/suggest/aws-transcribe/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 →