Amazon Transcribe
Amazon Transcribe is a managed speech-recognition service that turns live audio and recorded media into text.
What Amazon Transcribe is
Amazon Transcribe is a managed speech-recognition service that turns live audio and recorded media into text. It handles live streams for real-time transcription and files in Amazon S3 for batch processing, and supports 113 languages. Transcripts can include punctuation, formatted numbers, word timestamps, speaker and channel identification, and vocabulary filtering. The service can detect the dominant language or multiple languages without a language code; users can also add vocabulary or train language models with domain-specific text. Call Analytics provides sentiment, issue, speech-characteristic, categorization, and call-summary insights. Transcribe Medical supports dictation and conversational medical transcription and is HIPAA eligible. Privacy controls include personal-information redaction and toxic-content detection. Outputs can be encrypted at rest using S3 SSE-S3 or a customer-specified AWS KMS key, with TLS 1.2 in transit. Export formats are JSON, WebVTT, and SRT, and API access is available. The AWS CLI does not support streaming transcription.
Good
- Supports 113 languages.
- Handles live streams and S3 batch files.
- Includes speaker identification and word timestamps.
- Offers JSON, WebVTT, and SRT exports.
- Free tier provides 60 minutes monthly for 12 months.
Watch out
- AWS CLI does not support streaming transcription.
- Free-tier minutes do not roll over.
Who it suits
It suits developers and teams that need transcription for streaming audio or S3-stored recordings, with speaker labels, timestamps, or language customization. Call centers and medical transcription users may also find its specialized analytics and medical capabilities relevant.
Verdict
Amazon Transcribe covers live and recorded speech, with transcript controls, language customization, and specialized call and medical offerings. Check the streaming limitation if you expect to use the AWS CLI.
Plans and prices
From Amazon Transcribe's own pricing page, checked 1 Oct 2026.
| Plan | Price | What it gives you |
|---|---|---|
| Free tier | Free | unused monthly usage does not roll over · restrictions apply · 60 minutes per month for 12 months |
| Standard Batch | $0.01 a month | Pay-as-you-go batch transcription · Usage billed in one-second increments · No minimum usage · US East (N. Virginia) pricing example; rates vary by AWS Region and volume tier. |
| Standard Streaming | $0.01 a month | Pay-as-you-go streaming transcription · Usage billed in one-second increments · No minimum usage · US East (N. Virginia) pricing example; rates vary by AWS Region and volume tier. |
| Standard pricing | — | one-second increments · no minimum duration · rates vary by AWS Region · monthly based on seconds of audio transcribed |
The facts
Each one read from Amazon Transcribe's own pages, with the date it was checked.
What it does
- API access
- Yeschecked 20 Sep 2026
- AWS service integrations
- The product page identifies Amazon Connect Contact Lens and AWS HealthScribe as services used with Amazon Transcribe for call analytics and clinical documentation.checked 1 Oct 2026
- Call analytics
- Amazon Transcribe Call Analytics provides sentiment, issue, speech-characteristic, categorization, and generative call-summary insights.checked 1 Oct 2026
- Compliance
- Amazon Transcribe is covered under AWS HIPAA eligibility and BAA requirements.checked 1 Oct 2026
- Customization
- Users can add custom vocabulary and train custom language models with domain-specific text.checked 1 Oct 2026
- Encryption
- Transcription outputs can use Amazon S3 SSE-S3 or customer-specified AWS KMS keys at rest, while TLS 1.2 encrypts data in transit.checked 1 Oct 2026
- Export formats
- JSON,WebVTT,SRTchecked 20 Sep 2026
- Input modes
- The service processes live audio streams for real-time transcription and recorded media files stored in Amazon S3 for batch transcription.checked 1 Oct 2026
- Integrations
- Batch transcription uses Amazon S3, and AWS provides SDKs and CLI access for supported programming languages.checked 1 Oct 2026
- Language identification
- Amazon Transcribe can automatically identify the dominant language or multiple languages in audio without a specified language code.checked 1 Oct 2026
- Languages
- Amazon Transcribe provides features across 100+ languages.checked 1 Oct 2026
- Languages supported
- 113checked 20 Sep 2026
- Medical use
- Amazon Transcribe Medical supports dictation and conversational medical transcription and is HIPAA eligible.checked 1 Oct 2026
- Privacy controls
- Amazon Transcribe can filter vocabulary, redact personally identifiable information, and detect toxic audio content.checked 1 Oct 2026
- Purpose
- Amazon Transcribe is a fully managed automatic speech recognition service that converts streaming and recorded speech to text.checked 1 Oct 2026
- Speaker identification
- Yeschecked 20 Sep 2026
- Timestamp support
- Yeschecked 20 Sep 2026
- Transcript features
- It supports automatic punctuation, number formatting, word timestamps, speaker identification, channel identification, and vocabulary filtering.checked 1 Oct 2026
- Usage limit
- The AWS CLI does not support streaming transcriptions.checked 1 Oct 2026
Money
- Free plan
- Nochecked 20 Sep 2026
Alternatives to Amazon Transcribe
- 1
Whisper
Free planOpen sourceAPILinuxmacOSSelf-hosted8.9$0.01 usage-based - 2
Notta
Free planAndroidiOSWebExtension8.9From $8.17 a month - 3
Rev AI
Free planAndroidiOSWebAPI8.8Free plan - 4
Superwhisper
Free planAndroidiOSAPILinux8.7From $84.99 a year - 5
Happy Scribe
Free planAndroidiOSAPImacOS8.5From $8.50 a month - 6
Express Scribe
Free planAPILinuxmacOSWindows8.2Free plan