AssemblyAI Universal 3 Pro

Model Information
v3

Universal-3 Pro is the first production-quality speech model that adapts its behavior based on the instructions you provide. Every capability in Universal-3-Pro: audio tagging, disfluency capture, speaker labeling, works through prompting. Describe your audio in plain language and the model adjusts its transcription accordingly.

Model ID

assemblyai.universal-3-pro

Use this ID when making API calls to reference this model

Provider

assemblyai

Model Type

ASR

Accuracy Tier

premium

Release Date

February 3, 2026

Supported Languages

enesdefrptit
Automatic Language Detection: Yes

Streaming Transcription Languages

enen_auen_uken_usesfrdeitpt
Performance & Cost

Cost

$0.21000/hour

$0.00006/second

Maximum Duration

10h 0m

Maximum File Size

5.00 GB

Features

Supported capabilities and functionalities

Core Features

Punctuation
Diarization
Streaming
Speaker Labels
Word Timestamps
Confidence Scores
Custom Vocabulary
Profanity Filtering
Noise Reduction
Voice Activity Detection

Subtitle Formats

SRT Support
VTT Support
Technical Specifications

Input/output formats and technical details

Subtitle Format Support

No subtitle formats supported

Supported Audio Encodings

MP3WAVFLACAACM4A

Supported Sample Rates

8000 Hz16000 Hz22050 Hz44100 Hz48000 Hz