Models
AssemblyAI offers several state-of-the-art speech recognition models, each optimized for different use cases. Choose the model that best fits your needs based on accuracy, latency, cost, and language requirements.
Slam-1
Highest accuracy for transcribing English pre-recorded audio with fine-tuning support and customization via prompting
Universal
Best for out-of-the-box transcription of pre-recorded audio with multi-lingual support, excellent accuracy, and low latency
Nano
Most cost-effective transcription for pre-recorded audio with broad language support
Universal-Streaming
Streaming audio transcription optimized for voice agents and real-time applications
Choosing the right model
Slam-1
- Best for: English content requiring highest accuracy
- Key benefits:
- Superior accuracy for English content
- Fine-tuning support
- Ideal for domain-specific terminology
Universal
- Best for: Production-ready transcription out of the box
- Key benefits:
- Excellent accuracy-to-latency ratio
- Multi-language support
- No configuration needed
- Ideal for conversational intelligence
Nano
- Best for: Cost-sensitive applications with broad language needs
- Key benefits:
- Most cost-effective option
- Widest language support
Streaming
- Best for: Voice agents and real-time voice applications
- Key benefits:
- ~300ms immutable transcripts
- Continuous speech recognition
- Intelligent endpointing
- Ideal for voice agents and interactive applications
Pricing
For detailed pricing information, visit our pricing page.
For volume discounts, please reach out to sales@assemblyai.com.
Next steps
- For pre-recorded audio, see how to select your model
- For real-time transcription, check out our streaming documentation