Simple transparent pricing

Highest accuracy for English with fine-tuning support and customization via prompting

Fast, lightweight Speech AI at an accessible price point

Best for out-of-the-box transcription with excellent accuracy and low latency

Automatically detect the number of speakers in your audio file, and each word in the transcription text can be associated with its speaker.

Automatically detect if the dominant language of the spoken audio is supported by our API and route it to the appropriate model for transcription.

Automatically detect and replace profanity in the transcription text.

Only available in Nano. Boost accuracy for vocabulary that is unique or custom to your specific use case or product.

Only available in our Slam-1 model. Provide up to 1000 domain-specific words or phrases that may appear in your audio.

Transcribe audio files with multiple speakers separately.

Optionally include disfluencies in the transcripts of your audio files.

Specify how you would like certain words to be spelled or formatted in the transcription text.

Word-by-word timestamps across the entire transcript text.

Automatically add casing and punctuation of proper nouns to the transcription text.

Automatically add casing and punctuation of proper nouns to the transcription text.

Only available in Best tier. Boost accuracy for vocabulary that is unique or custom to your specific use case or product.

Customize End of Utterance Detection to more accurately detect when one speaker finishes an utterance in Streaming Speech-to-Text.

The newest and most advanced model featuring enhanced reasoning capabilities. Strong at complex reasoning tasks.

A mid-tier upgrade balancing power and performance.

The fastest model in the family, optimized for quick responses while maintaining good reasoning.

Claude 3 Opus is good at handling complex analysis, longer tasks with many steps, and higher-order math and coding tasks.

Claude 3 Haiku is the fastest model that can execute lightweight actions.

Identify a wide range of entities that are spoken in your audio files, such as person and company names, email addresses, dates, and locations.

Label the topics that are spoken in your audio and video files. The predicted topic labels follow the standardized IAB Taxonomy, which makes them suitable for contextual targeting.

Accurately identify significant words and phrases in your transcription, enabling you to extract the most pertinent concepts or highlights from your audio/video file.

Identify and remove Personally Identifiable Information, such as phone numbers and social security numbers, from the transcription text before it is returned to you.

With Sentiment Analysis, AssemblyAI can detect the sentiment of each sentence of speech spoken in your audio files.

Detect sensitive content in your audio and video files - such as hate speech, violence, sensitive social issues, alcohol, drugs, and more.

Automatically generate a summary over time for audio and video files.