AssemblyAI Sync API file limit vs Sume STT duration_seconds

AssemblyAI's launch post describes its Sync API as built for short clips and says the clip is decoded to a single 16 kHz audio array with no chunking; the post text I read states no byte or minute cap, so check AssemblyAI's own docs for the exact file limit. Sume's STT 1.0 numbers are explicit: duration_seconds takes 1 to 600, and omitting it reserves 1 minute.

AssemblyAI facts are from its launch post; Sume facts from the OpenAPI schema and docs, read 2026-10-01.

What does AssemblyAI say about clip length?

The post lists the Sync API for "short clips: dictation, voice agents with turn detection" and sends "long audio, batch, latency-tolerant" work to the Async API. It does not give a number in the part I read, so I do not quote one.

What are Sume's length numbers?

What happens if I leave duration_seconds out?

The reservation is one minute. For a 5-minute recording, send duration_seconds: 300 so the reservation matches the audio. The schema says the field improves the usage reservation; it is a hint for billing, not a cut-off you set on the audio.

What about audio longer than 10 minutes?

Split it into parts under 600 seconds and submit each as its own job, then join the word lists by offset. If the source is a video, Audio Detach can extract a 16 kHz mono track first; see audio detach for speech-to-text. Its own output limit is 900 s, so long files need a range there too.