Amazon Transcribe icon
audio-speech

Amazon Transcribe

Batch speech-to-text with word-level metadata, but accuracy drops on overlap and code-switching.

Visit Amazon Transcribe
Batch APIWord-level metadataSpeaker labels$0.006/min
TL;DR — our verdictUpdated September 2026 · 12 test artifacts

Reliable batch plumbing, uneven transcripts

Where it wins
  • you need a batch transcription API that returns word-level timestamps, confidence, and speaker labels
  • you can stage audio in S3 and run an async upload → poll → fetch workflow
  • you are transcribing mostly English or technical jargon and can tolerate weaker performance on overlap-heavy or code-switched audio
Main limitation
  • you need reliable multilingual or code-switching transcription
Pricing (verified plans)
Free tier $0Standard Batch $0.0001000/secStandard Streaming $0.0001667/sec
Strongest test artifacts
Batch Speech-to-Text Transcription →Structured Transcription Metadata Export →Asynchronous Batch Job Orchestration →

Our take

AWS Transcribe returned a complete developer payload on every scored run: word-level timing, confidence, and speaker labels were present, and the batch workflow completed cleanly at about $0.36/audio-hour. It was excellent on the medical-jargon clip, but it dropped heavily on overlapping speech and recovered only 30.0% of Spanish tokens in the code-switching sample. This benchmark also only verified speaker-label presence and count, not diarization attribution, so I would treat it as solid English-centric batch STT rather than a safe default for multilingual or overlap-heavy audio.

Download video: Demo videoWatch video (streaming): Demo video
Tutorial recording of the AWS Transcribe benchmark workflow.

In-Depth Review

Our detailed analysis of Amazon Transcribe — features, performance, and real-world testing.

AD
AI Demos Team
Expert Reviewer
Verified Review

Feature-by-Feature Breakdown

Batch Speech-to-Text Transcription
Mixed
▾
Test Summary
Feature tested: Batch Speech-to-Text Transcription
Result: Failed — Mixed

Feature tested: Batch Speech-to-Text Transcription

Result: Failed

Verdict: Mixed

Expected behavior: Converts staged long-form audio into full transcripts. It was exercised on overlapping crosstalk, medical-jargon, and bilingual code-switching clips.

Test case: Audio file → Image

Input type: Audio file

Input used: Input artifact (Audio file): INPUT: Overlapping Speech / Crosstalk — crosstalk.wav, 35:43, 65.39 MB, four-way overlapping meeting audio. — crosstalk.wav

Observed output: Output artifact (Image): Crosstalk transcript detail: WER 33.88% with 363 substitutions, 2162 deletions, and 43 insertions; the run detected 4 speaker labels. — 04-transcript-detail.png

Input artifact: Input artifact (Audio file): INPUT: Overlapping Speech / Crosstalk — crosstalk.wav, 35:43, 65.39 MB, four-way overlapping meeting audio. — crosstalk.wav

Output artifact: Output artifact (Image): Crosstalk transcript detail: WER 33.88% with 363 substitutions, 2162 deletions, and 43 insertions; the run detected 4 speaker labels. — 04-transcript-detail.png

What changed: Audio file transformed into Image

Test case: Audio file → Image

Input type: Audio file

Input used: Input artifact (Audio file): INPUT: Medical Jargon — medical_terms.mp3, 18:44, 8.58 MB, clean single-speaker medical narration. — medical_terms.mp3

Observed output: Output artifact (Image): Medical jargon transcript detail: WER 3.63%; it missed 'cancellous' and 'trabeculae' but still reached 77.8% jargon recall. — 04-transcript-detail-2.png

Input artifact: Input artifact (Audio file): INPUT: Medical Jargon — medical_terms.mp3, 18:44, 8.58 MB, clean single-speaker medical narration. — medical_terms.mp3

Output artifact: Output artifact (Image): Medical jargon transcript detail: WER 3.63%; it missed 'cancellous' and 'trabeculae' but still reached 77.8% jargon recall. — 04-transcript-detail-2.png

What changed: Audio file transformed into Image

Test case: Audio file → Image

Input type: Audio file

Input used: Input artifact (Audio file): INPUT: Bilingual Code-Switching — mix_language.mp3, 32:18, 22.19 MB, spontaneous Spanish-English conversation. — mix_language.mp3

Observed output: Output artifact (Image): Bilingual transcript detail: WER 23.06%; the error site dropped the Spanish token 'ahora' and the screen reported Spanish recall of 30.0%. — 04-transcript-detail-3.png

Input artifact: Input artifact (Audio file): INPUT: Bilingual Code-Switching — mix_language.mp3, 32:18, 22.19 MB, spontaneous Spanish-English conversation. — mix_language.mp3

Output artifact: Output artifact (Image): Bilingual transcript detail: WER 23.06%; the error site dropped the Spanish token 'ahora' and the screen reported Spanish recall of 30.0%. — 04-transcript-detail-3.png

What changed: Audio file transformed into Image

Test case: Audio file → Image

Input type: Audio file

Input used: Input artifact (Audio file): INPUT: Overlapping Speech / Crosstalk — verify the end-to-end batch job flow. — crosstalk.wav

Observed output: Output artifact (Image): Execution trace for crosstalk: multi-stage vendor protocol, no measured per-call count, 196.83s wall-clock latency, and 5,460 returned words from a 7,579-word reference. — 07-automation-trace.png

Input artifact: Input artifact (Audio file): INPUT: Overlapping Speech / Crosstalk — verify the end-to-end batch job flow. — crosstalk.wav

Output artifact: Output artifact (Image): Execution trace for crosstalk: multi-stage vendor protocol, no measured per-call count, 196.83s wall-clock latency, and 5,460 returned words from a 7,579-word reference. — 07-automation-trace.png

What changed: Audio file transformed into Image

Test case: Audio file → Image

Input type: Audio file

Input used: Input artifact (Audio file): INPUT: Medical Jargon — verify the end-to-end batch job flow. — medical_terms.mp3

Observed output: Output artifact (Image): Execution trace for medical jargon: multi-stage vendor protocol, no measured per-call count, 96.835s latency, and 2,728 returned words. — 07-automation-trace-2.png

Input artifact: Input artifact (Audio file): INPUT: Medical Jargon — verify the end-to-end batch job flow. — medical_terms.mp3

Output artifact: Output artifact (Image): Execution trace for medical jargon: multi-stage vendor protocol, no measured per-call count, 96.835s latency, and 2,728 returned words. — 07-automation-trace-2.png

What changed: Audio file transformed into Image

Test case: Audio file → Image

Input type: Audio file

Input used: Input artifact (Audio file): INPUT: Bilingual Code-Switching — verify the end-to-end batch job flow. — mix_language.mp3

Observed output: Output artifact (Image): Execution trace for bilingual code-switching: multi-stage vendor protocol, no measured per-call count, 172.18s latency, and 6,017 returned words. — 07-automation-trace-3.png

Input artifact: Input artifact (Audio file): INPUT: Bilingual Code-Switching — verify the end-to-end batch job flow. — mix_language.mp3

Output artifact: Output artifact (Image): Execution trace for bilingual code-switching: multi-stage vendor protocol, no measured per-call count, 172.18s latency, and 6,017 returned words. — 07-automation-trace-3.png

What changed: Audio file transformed into Image

Why it matters / Conclusion: Best on the medical-jargon clip, acceptable on the code-switching clip in headline WER, and clearly weakest on crosstalk because of heavy deletions.

Converts staged long-form audio into full transcripts. It was exercised on overlapping crosstalk, medical-jargon, and bilingual code-switching clips.

audio
0:00 / 0:00
Loading audio...
INPUT: Overlapping Speech / Crosstalk — crosstalk.wav, 35:43, 65.39 MB, four-way overlapping meeting audio.
↓
OUTPUT
Output artifact for "Batch Speech-to-Text Transcription" test: Crosstalk transcript detail: WER 33.88% with 363 substitutions, 2162 deletions, and 43 insertions; the run detected 4 speaker labels., 04-transcript-detail.png
Crosstalk transcript detail: WER 33.88% with 363 substitutions, 2162 deletions, and 43 insertions; the run detected 4 speaker labels.
audio
0:00 / 0:00
Loading audio...
INPUT: Medical Jargon — medical_terms.mp3, 18:44, 8.58 MB, clean single-speaker medical narration.
↓
OUTPUT
Output artifact for "Batch Speech-to-Text Transcription" test: Medical jargon transcript detail: WER 3.63%; it missed 'cancellous' and 'trabeculae' but still reached 77.8% jargon recall., 04-transcript-detail-2.png
Medical jargon transcript detail: WER 3.63%; it missed 'cancellous' and 'trabeculae' but still reached 77.8% jargon recall.
audio
0:00 / 0:00
Loading audio...
INPUT: Bilingual Code-Switching — mix_language.mp3, 32:18, 22.19 MB, spontaneous Spanish-English conversation.
↓
OUTPUT
Output artifact for "Batch Speech-to-Text Transcription" test: Bilingual transcript detail: WER 23.06%; the error site dropped the Spanish token 'ahora' and the screen reported Spanish recall of 30.0%., 04-transcript-detail-3.png
Bilingual transcript detail: WER 23.06%; the error site dropped the Spanish token 'ahora' and the screen reported Spanish recall of 30.0%.
audio
0:00 / 0:00
Loading audio...
INPUT: Overlapping Speech / Crosstalk — verify the end-to-end batch job flow.
↓
OUTPUT
Output artifact for "Batch Speech-to-Text Transcription" test: Execution trace for crosstalk: multi-stage vendor protocol, no measured per-call count, 196.83s wall-clock latency, and 5,460 returned words from a 7,579-word reference., 07-automation-trace.png
Execution trace for crosstalk: multi-stage vendor protocol, no measured per-call count, 196.83s wall-clock latency, and 5,460 returned words from a 7,579-word reference.
audio
0:00 / 0:00
Loading audio...
INPUT: Medical Jargon — verify the end-to-end batch job flow.
↓
OUTPUT
Output artifact for "Batch Speech-to-Text Transcription" test: Execution trace for medical jargon: multi-stage vendor protocol, no measured per-call count, 96.835s latency, and 2,728 returned words., 07-automation-trace-2.png
Execution trace for medical jargon: multi-stage vendor protocol, no measured per-call count, 96.835s latency, and 2,728 returned words.
audio
0:00 / 0:00
Loading audio...
INPUT: Bilingual Code-Switching — verify the end-to-end batch job flow.
↓
OUTPUT
Output artifact for "Batch Speech-to-Text Transcription" test: Execution trace for bilingual code-switching: multi-stage vendor protocol, no measured per-call count, 172.18s latency, and 6,017 returned words., 07-automation-trace-3.png
Execution trace for bilingual code-switching: multi-stage vendor protocol, no measured per-call count, 172.18s latency, and 6,017 returned words.
Bottom Line
Best on the medical-jargon clip, acceptable on the code-switching clip in headline WER, and clearly weakest on crosstalk because of heavy deletions.
From our researchearlier researchTranscribe Audio Accurately — Speech-to-Text Engine Benchmark
Structured Transcription Metadata Export
Strong developer payload shape, but transcript quality varies sharply by audio type.
▾
Test Summary
Feature tested: Structured Transcription Metadata Export
Result: Partial — Strong developer payload shape, but transcript quality varies sharply by audio type.

Feature tested: Structured Transcription Metadata Export

Result: Partial

Verdict: Strong developer payload shape, but transcript quality varies sharply by audio type.

Expected behavior: Returns batch transcription output together with word-level timestamps, confidence values, and speaker-label fields, often in a developer-facing JSON shape. It was exercised on medical-jargon narration, four-speaker crosstalk, and bilingual code-switching clips.

Test case: Audio file → Text/code file

Input type: Audio file

Input used: Input artifact (Audio file): INPUT: Overlapping Speech / Crosstalk — a four-person meeting recording (35:43, 65.4 MB) used to test overlap and speaker separation. — crosstalk.wav

Observed output: Output artifact (Text/code file): Completed JSON response for the crosstalk run: status COMPLETED, transcript text returned, speaker_labels present, 5912 timed tokens, and 4 detected speakers. The benchmark later scored this clip at 33.88% WER with heavy deletions. — raw-response-input-1.json

Input artifact: Input artifact (Audio file): INPUT: Overlapping Speech / Crosstalk — a four-person meeting recording (35:43, 65.4 MB) used to test overlap and speaker separation. — crosstalk.wav

Output artifact: Output artifact (Text/code file): Completed JSON response for the crosstalk run: status COMPLETED, transcript text returned, speaker_labels present, 5912 timed tokens, and 4 detected speakers. The benchmark later scored this clip at 33.88% WER with heavy deletions. — raw-response-input-1.json

What changed: Audio file transformed into Text/code file

Test case: Audio file → Text/code file

Input type: Audio file

Input used: Input artifact (Audio file): INPUT: Medical Jargon — clean single-speaker narration from Gray's Anatomy via LibriVox (18:44, 8.6 MB) used to test lexical precision. — medical_terms.mp3

Observed output: Output artifact (Text/code file): Completed JSON response for the medical-jargon run: status COMPLETED, transcript text returned, speaker_labels present, 2829 timed tokens, and a single detected speaker in the previewed segment. The benchmark later scored this clip at 3.63% WER, with jargon recall at 77.8% and misses on cancellous and trabeculae. — raw-response-input-2.json

Input artifact: Input artifact (Audio file): INPUT: Medical Jargon — clean single-speaker narration from Gray's Anatomy via LibriVox (18:44, 8.6 MB) used to test lexical precision. — medical_terms.mp3

Output artifact: Output artifact (Text/code file): Completed JSON response for the medical-jargon run: status COMPLETED, transcript text returned, speaker_labels present, 2829 timed tokens, and a single detected speaker in the previewed segment. The benchmark later scored this clip at 3.63% WER, with jargon recall at 77.8% and misses on cancellous and trabeculae. — raw-response-input-2.json

What changed: Audio file transformed into Text/code file

Test case: Audio file → Text/code file

Input type: Audio file

Input used: Input artifact (Audio file): INPUT: Bilingual Code-Switching — spontaneous Spanish-English conversation (32:18, 22.2 MB) used to test code-switching and language routing. — mix_language.mp3

Observed output: Output artifact (Text/code file): Completed JSON response for the bilingual run: status COMPLETED, transcript text returned, speaker_labels present, 6311 timed tokens, and 3 detected speakers. The benchmark later scored this clip at 23.06% WER, with Spanish token recall at 30.0% and many Spanish words dropped or anglicized. — raw-response-input-3.json

Input artifact: Input artifact (Audio file): INPUT: Bilingual Code-Switching — spontaneous Spanish-English conversation (32:18, 22.2 MB) used to test code-switching and language routing. — mix_language.mp3

Output artifact: Output artifact (Text/code file): Completed JSON response for the bilingual run: status COMPLETED, transcript text returned, speaker_labels present, 6311 timed tokens, and 3 detected speakers. The benchmark later scored this clip at 23.06% WER, with Spanish token recall at 30.0% and many Spanish words dropped or anglicized. — raw-response-input-3.json

What changed: Audio file transformed into Text/code file

Why it matters / Conclusion: Best when you need a batch transcript plus metadata in a stable JSON shape; not best when you need uniformly accurate transcription across hard audio, and not enough to prove diarization attribution on its own.

Returns batch transcription output together with word-level timestamps, confidence values, and speaker-label fields, often in a developer-facing JSON shape. It was exercised on medical-jargon narration, four-speaker crosstalk, and bilingual code-switching clips.

audio
0:00 / 0:00
Loading audio...
INPUT: Overlapping Speech / Crosstalk — a four-person meeting recording (35:43, 65.4 MB) used to test overlap and speaker separation.
↓
OUTPUT
raw-response-input-1.json
Loading file...
Completed JSON response for the crosstalk run: status COMPLETED, transcript text returned, speaker_labels present, 5912 timed tokens, and 4 detected speakers. The benchmark later scored this clip at 33.88% WER with heavy deletions.
audio
0:00 / 0:00
Loading audio...
INPUT: Medical Jargon — clean single-speaker narration from Gray's Anatomy via LibriVox (18:44, 8.6 MB) used to test lexical precision.
↓
OUTPUT
raw-response-input-2.json
Loading file...
Completed JSON response for the medical-jargon run: status COMPLETED, transcript text returned, speaker_labels present, 2829 timed tokens, and a single detected speaker in the previewed segment. The benchmark later scored this clip at 3.63% WER, with jargon recall at 77.8% and misses on cancellous and trabeculae.
audio
0:00 / 0:00
Loading audio...
INPUT: Bilingual Code-Switching — spontaneous Spanish-English conversation (32:18, 22.2 MB) used to test code-switching and language routing.
↓
OUTPUT
raw-response-input-3.json
Loading file...
Completed JSON response for the bilingual run: status COMPLETED, transcript text returned, speaker_labels present, 6311 timed tokens, and 3 detected speakers. The benchmark later scored this clip at 23.06% WER, with Spanish token recall at 30.0% and many Spanish words dropped or anglicized.
Bottom Line
Best when you need a batch transcript plus metadata in a stable JSON shape; not best when you need uniformly accurate transcription across hard audio, and not enough to prove diarization attribution on its own.
From our researchearlier researchTranscribe Audio Accurately — Speech-to-Text Engine Benchmark
Asynchronous Batch Job Orchestration
End-to-end batch orchestration worked on all three runs.
▾
Test Summary
Feature tested: Asynchronous Batch Job Orchestration
Result: Passed — End-to-end batch orchestration worked on all three runs.

Feature tested: Asynchronous Batch Job Orchestration

Result: Passed

Verdict: End-to-end batch orchestration worked on all three runs.

Expected behavior: Submits audio as a signed batch request, stages it in S3, polls for completion, and retrieves the finished transcription result. It was exercised with a local AWS profile when available and credential prompting at runtime.

Test case: Audio file → Image

Input type: Audio file

Input used: Input artifact (Audio file): INPUT: Overlapping Speech / Crosstalk batch transcription job with AWS-signed auth and speaker labels enabled. — crosstalk.wav

Observed output: Output artifact (Image): Execution trace shows crosstalk.wav submitted, multi-stage HTTP protocol, status scored, 196.83s wall clock, RTF 0.09186, cost $0.21427, and 5,460 returned words versus 7,579 reference words. Per-call timings were not instrumented in this run. — 07-automation-trace-input-1.png

Input artifact: Input artifact (Audio file): INPUT: Overlapping Speech / Crosstalk batch transcription job with AWS-signed auth and speaker labels enabled. — crosstalk.wav

Output artifact: Output artifact (Image): Execution trace shows crosstalk.wav submitted, multi-stage HTTP protocol, status scored, 196.83s wall clock, RTF 0.09186, cost $0.21427, and 5,460 returned words versus 7,579 reference words. Per-call timings were not instrumented in this run. — 07-automation-trace-input-1.png

What changed: Audio file transformed into Image

Test case: Audio file → Image

Input type: Audio file

Input used: Input artifact (Audio file): INPUT: Medical Jargon batch transcription job with AWS-signed auth and speaker labels enabled. — medical_terms.mp3

Observed output: Output artifact (Image): Execution trace shows medical_terms.mp3 submitted, multi-stage HTTP protocol, status scored, 96.83s wall clock, RTF 0.08615, cost $0.1124, and 2,728 returned words versus 2,728 reference words. Per-call timings were not instrumented in this run. — 07-automation-trace-input-2.png

Input artifact: Input artifact (Audio file): INPUT: Medical Jargon batch transcription job with AWS-signed auth and speaker labels enabled. — medical_terms.mp3

Output artifact: Output artifact (Image): Execution trace shows medical_terms.mp3 submitted, multi-stage HTTP protocol, status scored, 96.83s wall clock, RTF 0.08615, cost $0.1124, and 2,728 returned words versus 2,728 reference words. Per-call timings were not instrumented in this run. — 07-automation-trace-input-2.png

What changed: Audio file transformed into Image

Test case: Audio file → Image

Input type: Audio file

Input used: Input artifact (Audio file): INPUT: Bilingual Code-Switching batch transcription job with AWS-signed auth and speaker labels enabled. — mix_language.mp3

Observed output: Output artifact (Image): Execution trace shows mix_language.mp3 submitted, multi-stage HTTP protocol, status scored, 172.18s wall clock, RTF 0.08882, cost $0.19385, and 6,017 returned words versus 6,517 reference words. Per-call timings were not instrumented in this run. — 07-automation-trace-input-3.png

Input artifact: Input artifact (Audio file): INPUT: Bilingual Code-Switching batch transcription job with AWS-signed auth and speaker labels enabled. — mix_language.mp3

Output artifact: Output artifact (Image): Execution trace shows mix_language.mp3 submitted, multi-stage HTTP protocol, status scored, 172.18s wall clock, RTF 0.08882, cost $0.19385, and 6,017 returned words versus 6,517 reference words. Per-call timings were not instrumented in this run. — 07-automation-trace-input-3.png

What changed: Audio file transformed into Image

Why it matters / Conclusion: The batch workflow itself was stable across all three runs, but the benchmark did not measure call-by-call HTTP timings, so this confirms end-to-end automation rather than internal stage latency.

Submits audio as a signed batch request, stages it in S3, polls for completion, and retrieves the finished transcription result. It was exercised with a local AWS profile when available and credential prompting at runtime.

audio
0:00 / 0:00
Loading audio...
INPUT: Overlapping Speech / Crosstalk batch transcription job with AWS-signed auth and speaker labels enabled.
↓
OUTPUT
Output artifact for "Asynchronous Batch Job Orchestration" test: Execution trace shows crosstalk.wav submitted, multi-stage HTTP protocol, status scored, 196.83s wall clock, RTF 0.09186, cost $0.21427, and 5,460 returned words versus 7,579 reference words. Per-call timings were not instrumented in this run., 07-automation-trace-input-1.png
Execution trace shows crosstalk.wav submitted, multi-stage HTTP protocol, status scored, 196.83s wall clock, RTF 0.09186, cost $0.21427, and 5,460 returned words versus 7,579 reference words. Per-call timings were not instrumented in this run.
audio
0:00 / 0:00
Loading audio...
INPUT: Medical Jargon batch transcription job with AWS-signed auth and speaker labels enabled.
↓
OUTPUT
Output artifact for "Asynchronous Batch Job Orchestration" test: Execution trace shows medical_terms.mp3 submitted, multi-stage HTTP protocol, status scored, 96.83s wall clock, RTF 0.08615, cost $0.1124, and 2,728 returned words versus 2,728 reference words. Per-call timings were not instrumented in this run., 07-automation-trace-input-2.png
Execution trace shows medical_terms.mp3 submitted, multi-stage HTTP protocol, status scored, 96.83s wall clock, RTF 0.08615, cost $0.1124, and 2,728 returned words versus 2,728 reference words. Per-call timings were not instrumented in this run.
audio
0:00 / 0:00
Loading audio...
INPUT: Bilingual Code-Switching batch transcription job with AWS-signed auth and speaker labels enabled.
↓
OUTPUT
Output artifact for "Asynchronous Batch Job Orchestration" test: Execution trace shows mix_language.mp3 submitted, multi-stage HTTP protocol, status scored, 172.18s wall clock, RTF 0.08882, cost $0.19385, and 6,017 returned words versus 6,517 reference words. Per-call timings were not instrumented in this run., 07-automation-trace-input-3.png
Execution trace shows mix_language.mp3 submitted, multi-stage HTTP protocol, status scored, 172.18s wall clock, RTF 0.08882, cost $0.19385, and 6,017 returned words versus 6,517 reference words. Per-call timings were not instrumented in this run.
Bottom Line
The batch workflow itself was stable across all three runs, but the benchmark did not measure call-by-call HTTP timings, so this confirms end-to-end automation rather than internal stage latency.
From our researchTranscribe Audio Accurately — Speech-to-Text Engine Benchmarkearlier research

How it scored on the research's own criteria

The 3 evaluation dimensions from our hands-on research on Amazon Transcribe, each judged from recorded runs on 3 test inputs — the same verdicts the ranking page ranks on.

held up  partial  failed  not exercised by this input

CriterionVerdictWhat the runs showedPer inputProof
Output qualityMixed3/5Accuracy swings from very good on the medical narration to poor on overlapping speech and code-switching, so the overall picture is mixed rather than strong: it can produce a usable transcript, but it loses too much content when the audio gets harder.open proof ↗
Automation levelStrong5/5Every run finished from upload through scored result without a human stepping in, and the setup handled credentials automatically; the missing per-call timings affect trace detail, not whether the workflow was fully automated.open proof ↗
Input handlingStrong4/5It took all three files without objection, processed them at roughly 0.09 RTF, and stayed at list-price cost; the only thing that keeps this from a top score is that it is batch-only here, so faster live/streaming behavior was never exercised.open proof ↗

Verdicts come verbatim from the study's recorded observations, never re-derived at render; a criterion with no recorded run shows Not exercised — this section cannot invent a score.

AWS Transcribe pricing

Standard batch is flat-rate and was the mode used in this benchmark.

Free tier
$0
60 audio minutes/month for 12 months; unused minutes do not roll over.
TESTED
Standard Batch
$0.0001000/sec ($0.006/min)
Flat rate, no volume tiers, billed in 1-second increments; this benchmark used standard batch.
Standard Streaming
$0.0001667/sec ($0.010002/min)
Flat rate shown in the report, but this benchmark was batch-only and did not measure streaming latency.

Standard transcription is billed in 1-second increments with no minimum. The report also says the free tier is 60 audio minutes per month for 12 months. Add-ons such as automatic content redaction and custom language models are priced separately.

✓ Use This If
●you need a batch transcription API that returns word-level timestamps, confidence, and speaker labels
●you can stage audio in S3 and run an async upload → poll → fetch workflow
●you are transcribing mostly English or technical jargon and can tolerate weaker performance on overlap-heavy or code-switched audio
✕ Skip This If
●you need reliable multilingual or code-switching transcription
●you need verified diarization attribution rather than just detected speaker labels
●you need direct local-file transcription without S3 staging
●you need measured streaming latency from this benchmark
audio-speechaudio-to-textspeechOther
Yes in this benchmark. The request configuration notes that audio must be staged in S3 first, then the pipeline uses AWS-signed batch requests to start and fetch the job.
On all three scored runs the payload included word-level timestamps, confidence, and speaker_labels. Payload depth was 3/3 on every input.
Yes. Speaker labels were returned on every run, and the previewed counts were 4 speakers on crosstalk, 1 on medical jargon, and 3 on the bilingual sample. The benchmark did not measure whether those labels were attributed correctly.
Poorly. On the four-speaker crosstalk sample it scored 33.88% WER, returned 5,460 words versus 7,579 reference words, and dropped a large amount of content.
Weakly on Spanish content. The benchmark recorded 23.06% WER overall and only 30.0% Spanish token recall, with many Spanish tokens dropped or anglicized.
Standard batch is $0.006/min ($0.36/audio-hour) and the report says the free tier is 60 audio minutes per month for 12 months. The benchmarked standard batch mode is flat-rate with no volume tiers.

Banner Preview

How the embed badge will look on your site

Amazon Transcribe featured on AI Demos

Embed HTML

Copy this code to your website source

<a target="_blank" href="https://aidemos.com/tools/aws-transcribe?utm_source=aws-transcribe_embed" style="width: 250px; height: 80px; border-radius:4px;" width="250" height="80"> <img src="https://aidemos-website-images.s3.amazonaws.com/featured.png" alt="Amazon Transcribe | Featured on AI Demos" style="width: 250px; height: 80px; border-radius:4px;" width="250" height="80"> </a>

Quick Integration Guide

  • 1Copy the HTML code block above.
  • 2Paste it into your site's HTML or CMS editor.
  • 3Banner appears instantly on your page.
  • 4Links back to your tool profile here.
Similar Tools

Similar Tools

Discover more AI tools like Amazon Transcribe to enhance your workflow.

🤖
Gladia (Solaria)
AI Tool
🤖
Deepgram Nova-3
AI Tool
🤖
AssemblyAI
Fast batch speech-to-text with rich metadata, strong jargon and mixed-language results, but overlap-heavy meetings can still lose too much.
AI Tool
🤖
Speechmatics
Strong batch STT for hard English audio, but weak on code-switching as configured.
AI Tool
🤖
OpenAI
Batch speech-to-text with word timestamps, but a strict upload cap and weak multilingual performance make it a mixed fit for hard audio.
AI Tool
🤖
Google Cloud STT v2
AI Tool
🤖
ElevenLabs Scribe
Fast batch speech-to-text with word-level metadata, strongest on jargon and weaker on overlap/code-switching.
AI Tool
🤖
Rev AI
Low-cost batch speech-to-text with structured JSON, word timestamps, and speaker labels, but mixed accuracy on crosstalk and code-switching.
AI Tool
🤖
GroqCloud Whisper Large-v3
AI Tool
🤖
Gladia
Batch STT with rich word-level metadata and strong jargon recall, but overlap handling is weak and bilingual WER needs a mono-downmixed rerun.
AI Tool
🤖
Deepgram
Batch speech-to-text with word-level metadata and speaker labels, but weak on crosstalk and code-switching.
AI Tool
🤖
OpenAI Whisper-1
AI Tool
🤖
Gladia Solaria
AI Tool
🤖
AssemblyAI Universal
AI Tool
🤖
Speechmatics Ursa Enhanced
AI Tool
🤖
Google Cloud Speech-to-Text Chirp 2
AI Tool
🤖
Microsoft Azure Speech Services
AI Tool

Comments (0)

Please Log in to join the discussion.

Built by FutureSmart AI — the team behind AI Demos

Need a custom AI solution for this use case?

If you are looking to build a custom speech-to-text, audio transcription, or subtitle generation system for your business or internal workflow, email us at contact@futuresmart.ai.

Get a custom build

Found something inaccurate or missing? We try to keep our AI research accurate and useful. If you found outdated information, an issue, or have a suggestion, email us at collaborate@aidemos.com.

Back to Top