Cartesia Ink vs Rev AI Speech-to-Text API

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.

Rev AI Speech-to-Text API

Reverb English at $0.20 an hour, foreign languages at $0.30. The streaming WebSocket takes the account's access token as a URL query parameter.

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.

Rev AI Speech-to-Text API

1. Keep streaming URLs out of logs. They carry access_token
2. Send source_config: {"url": ...}, not media_url, even though the published SDKs still use media_url
3. Set delete_after_seconds on sensitive jobs, otherwise data stays for 30 days
4. Use notification_config webhooks rather than polling job status
5. Don't build on low_cost or fusion. Both are deprecated