universal-3-5-pro
AssemblyAI's recommended pre-recorded model (highest accuracy, 18 languages, code switching, contextual prompting), also available as the previous-flagship streaming model.
01 Price
$0.21per hour
Cheaper than 79% of 236 priced speech-to-text and realtime models.
Speech-to-text and realtime $ per hour of audio, log scale 236 priced
other models this modelAll models by price
| Plan or mode | Price |
|---|---|
| Streaming (Universal-3.5 Pro Realtime, per hour of session duration) | $0.45 per hour |
| Keyterms prompting add-on (pre-recorded) | $0.05 per hour |
| Speaker diarization add-on (async standard) | $0.02 per hour |
| Speaker diarization add-on (async experimental) | $0.07 per hour |
Pre-recorded pro-rated per second. Streaming rate from docs Models pricing table (pricing page lists only 3.6 Pro Realtime). Other add-ons (/hr): sentiment 0.02, summarization 0.02-0.07, topic detection 0.15, entity detection 0.08, PII text 0.08, PII audio 0.05, medical mode 0.15.
Pricing source, checked 2026-11-16
02 Languages 18
03 Features 11 of 11 listed
- Word timestamps
- Speaker diarization
- Punctuation
- Profanity filter
- Custom vocabulary
- Language detection
- Translation
- Sentiment
- PII redaction
- Summarization
- Topic detection
"Not listed" means the provider's data doesn't mention it, not that the model lacks it.
04 Get this record
curl https://voicedex.dev/v1/providers/assemblyai/models/universal-3-5-pro
Free, no key needed. Use model id universal-3-5-pro with AssemblyAI's own API. API reference.