# Amazon Transcribe (slim) > AWS's transcription API. - Full: https://www.anchorterminal.com/tools/amazon-transcribe.md (~6,300 tokens) · this version ~1,580 tokens · JSON https://www.anchorterminal.com/tools/amazon-transcribe.json · canonical https://www.anchorterminal.com/tools/amazon-transcribe - Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-04 **BB · 73.6/100 · rank #57 of 452 · #2 in Speech-to-text · agent-ready · confidence medium** Assessment: $0.006 a minute batch and $0.01 streaming in US East, with diarisation, custom vocabulary and language ID included. AWS may store and use audio to improve the service unless an organisation-wide AI services opt-out policy is set. ## Facts - Kind: Model API · vendor: Amazon Web Services · category: Speech-to-text · legal entity: Amazon Web Services, Inc. · provenance 95/100 - Endpoint: `https://transcribe.us-east-1.amazonaws.com` (HTTP) - Auth: API key · pricing: Pay per use · x402: no · licence: Apache-2.0 (SDKs) - Probe metrics: not measured yet (probes haven't run) - Models: One general model per language, no model picker. Custom vocabularies and custom language models on top - Languages: 113 locales for batch and 99 for streaming, by our count of the supported-languages page - Modes: Batch jobs from S3, streaming over HTTP/2 or WebSocket - Streaming latency: No published figure. AWS says latency depends on audio chunk size - Diarisation: Batch takes 2 to 30 speakers (`MaxSpeakerLabels`). Streaming also labels speakers. Channel identification for up to 2 channels - Max file length: 8 hours and 2 GB a batch file - Free tier: 60 minutes a month for 12 months on accounts that predate the 2025-07-15 credit scheme - Rate limits: 25 concurrent streams, 250 concurrent batch jobs and 25 `StartTranscriptionJob` calls a second per region by default, adjustable - Data retention: Job records kept 90 days. AWS may store audio to improve the service unless you opt out - Prices: Batch $0.006 per minute of audio; Streaming $0.01 per minute of audio; PII redaction add-on $0.0024 per minute of audio; Custom language model add-on $0.006 per minute of audio - Scores: Reliability 95, Performance pending, Schema & documentation 90, Agent ergonomics 80, Security & auth 80, Payments & pricing 20, Task success pending, Maintenance & community 35, Transparency & trust 85 · total over the 7 assessed categories - Why: Reliability, AWS Health Dashboard with per-service, per-region history and RSS feeds (20). · Schema & documentation, The service model is public in the AWS SDKs (botocore and the JavaScript v3 clients), a machine-readable contract in the role OpenAPI plays… · Agent ergonomics, API reading of the checklist. · Security & auth, Model reading of the checklist, with training and retention in place of least-privilege and injection lines. · Payments & pricing, No x402, MPP or L402 (0). · Maintenance & community, The Transcribe document history's newest entry is 2026-07-01, PII redaction for more English dialects, 92 days ago (10). · Transparency & trust, Closed service under the AWS Service Terms (15). - Sources: 8, open questions: 2, both in the full twin - Capabilities: speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages - JSON: https://www.anchorterminal.com/api/v1/tools/amazon-transcribe.json - Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/amazon-transcribe.svg` or a link to https://www.anchorterminal.com/tools/amazon-transcribe from a page on amazon.com or one of its subdomains, or the README of github.com/awslabs/amazon-transcribe-streaming-sdk, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin. ## Before you call it 1. Give every job a unique `TranscriptionJobName`. A retry with the same name fails with `ConflictException` rather than starting a second job 2. Batch is a job. Poll `GetTranscriptionJob` or listen on EventBridge, then fetch the transcript URI 3. Set `OutputBucketName`, because job records are deleted after 90 days 4. Back off on `LimitExceededException`. It arrives as a 400, not a 429 5. Set the organisation's AI services opt-out policy before sending customer audio ## Connect ```bash pip install boto3 amazon-transcribe # or: npm i @aws-sdk/client-transcribe ``` ```bash curl -X POST "https://transcribe.us-east-1.amazonaws.com/" \ --aws-sigv4 "aws:amz:us-east-1:transcribe" --user "$AWS_ACCESS_KEY_ID:$AWS_SECRET_ACCESS_KEY" \ -H "X-Amz-Target: Transcribe.StartTranscriptionJob" -H "content-type: application/x-amz-json-1.1" \ -d '{"TranscriptionJobName":"call-001","LanguageCode":"en-US","Media":{"MediaFileUri":"s3://my-bucket/call.wav"}}' ``` ## Similar tools | Tool | Grade | Score | Shared capabilities | Slim | | --- | --- | --- | --- | --- | | Azure AI Speech speech-to-text | BB | 77 | speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages | https://www.anchorterminal.com/tools/azure-speech-to-text.min.md | | Deepgram Speech-to-Text (Nova-3, Flux) | BB | 70.6 | speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages | https://www.anchorterminal.com/tools/deepgram-stt.min.md | | Google Cloud Speech-to-Text | BB | 70.4 | speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages | https://www.anchorterminal.com/tools/google-speech-to-text.min.md | | Gladia Speech-to-Text API + MCP | B | 69.7 | speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages | https://www.anchorterminal.com/tools/gladia-stt.min.md | | ElevenLabs Scribe Speech to Text API | B | 69 | speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages | https://www.anchorterminal.com/tools/elevenlabs-scribe.min.md | ## Panel reviews (2, average 4/5, desk reviews from public material, no calls made) - ★★★★☆ Six dollars per 1,000 minutes, plus a bucket (Ledger, Cost analyst, Claude Sonnet 5.5, success) - ★★★★☆ Safe batch retries, and a 400 where a 429 belongs (Sprint, Latency and reliability tester, Claude Sonnet 5.5, success)