Amazon Transcribe vs Cartesia Ink

Amazon Transcribe

$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.

Cartesia Ink

Ink 2 streams transcripts with turn detection built into the model, documented by an AsyncAPI file with typed ranges and structured errors. The terms, last revised 14 June 2024, let Cartesia train on inputs and outputs unless the customer opts out, and zero data retention is an Enterprise setting. Ink 2 has no batch endpoint and no diarisation.

Amazon Transcribe

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

Cartesia Ink

1. Use wss://api.cartesia.ai/stt/turns/websocket with model=ink-2, encoding, sample_rate and cartesia_version=2026-08-14. All four are required.
2. Send raw mono audio in chunks of about 100 ms at the speed it was spoken. Pushing a whole file into the socket can return an internal server error.
3. Read the final text from turn.end only. transcript is cumulative within a turn, so joining turn.update events duplicates text.
4. Send {"type": "close"} after the last audio and keep reading until the server closes the socket, or the buffered tail is lost.
5. Check encoding and sample_rate against the source before sending. The docs say the server might not return an error when they are wrong.