See how AssemblyAI performs on your audio
Request a customized benchmark across AssemblyAI models and alternative providers. Our team will be in touch shortly.
Customized testing using your actual audio files and real-world scenarios- Detailed methodology documentation so you understand exactly how results were generated
- Clear visualization of performance differences that matter to your business
- BAA and NDA available upon request
Accuracy*
Available languages
Hours of multilingual data
Streaming latency
Pricing without the lock-in
Get started for free. $0.15/hr after that – no commitments, no minimums, no credit card to get started.
Pre-recorded Speech-to-Text API
Models | Pay as you go | Custom |
|---|---|---|
Universal-3 Pro Identify a wide range of entities that are spoken in your audio files, such as person and company names, email addresses, dates, and locations.  Our most accurate speech-to-text model, leading the market in multilingual accuracy on WER, entities, rare words, alphanumerics, and messy speech in real-world audio. Currently supports English, Spanish, German, French, Italian, and Portuguese with more languages coming soon. Identify a wide range of entities that are spoken in your audio files, such as person and company names, email addresses, dates, and locations. | $0.21/hr | |
Universal-2 Identify a wide range of entities that are spoken in your audio files, such as person and company names, email addresses, dates, and locations. Our highly accurate speech-to-text model trained on over 12.5 million hours of audio data. Supports 99 languages. Exceptional accuracy at a lower price. Identify a wide range of entities that are spoken in your audio files, such as person and company names, email addresses, dates, and locations. | $0.15/hr | |
ADD-ON FEATURES | Universal-3 Pro | Universal-2 |
|---|---|---|
Keyterms Prompting Identify a wide range of entities that are spoken in your audio files, such as person and company names, email addresses, dates, and locations. Provide up to 1000 words or phrases (maximum 6 words per phrase) to improve transcription accuracy. | $0.05/hr | Included |
Control transcription behavior with plain language instructions: provide context, tag audio events, and more. | $0.05/hr | Not supported |
Speaker Diarization Identify a wide range of entities that are spoken in your audio files, such as person and company names, email addresses, dates, and locations. Detect multiple speakers in audio files and segment the transcript into utterances, showing what each speaker said. | $0.02/hr | $0.02/hr |
Medical Mode Identify a wide range of entities that are spoken in your audio files, such as person and company names, email addresses, dates, and locations. New Optimize transcription for medical terminology and healthcare conversations with significantly improved accuracy. | $0.15/hr | $0.15/hr |
Ready to A/B test in production?
Streaming Speech-to-Text API
Models | Pay as you go | Custom |
|---|---|---|
Universal-3 Pro Streaming New Speaker Identification allows you to identify speakers by their actual names or roles, transforming generic labels like “Speaker A” or “Speaker B” into meaningful identifiers that you provide. The most accurate model for voice agents that demand the highest quality. Best-in-class accuracy with advanced prompting capabilities. Supports English, Spanish, German, French, Portuguese, and Italian. | $0.45/hr | |
Universal-Streaming Identify a wide range of entities that are spoken in your audio files, such as person and company names, email addresses, dates, and locations. Speaker Identification allows you to identify speakers by their actual names or roles, transforming generic labels like “Speaker A” or “Speaker B” into meaningful identifiers that you provide. The fastest model for real-time English transcription. Optimized for speed and cost-effectiveness for English-only applications. | $0.15/hr | |
Universal-Streaming Multilingual Identify a wide range of entities that are spoken in your audio files, such as person and company names, email addresses, dates, and locations. Speaker Identification allows you to identify speakers by their actual names or roles, transforming generic labels like “Speaker A” or “Speaker B” into meaningful identifiers that you provide. Multilingual transcription at the speed and cost of Universal-Streaming. Supports English, Spanish, German, French, Portuguese, and Italian. | $0.15/hr | |
Whisper-Streaming Identify a wide range of entities that are spoken in your audio files, such as person and company names, email addresses, dates, and locations. Identify a wide range of entities that are spoken in your audio files, such as person and company names, email addresses, dates, and locations. Speaker Identification allows you to identify speakers by their actual names or roles, transforming generic labels like “Speaker A” or “Speaker B” into meaningful identifiers that you provide. Open-source Whisper model enhanced with AssemblyAI's reliable infrastructure and unlimited scale. Supports 99+ languages at an accessible price point. | $0.30/hr | |
Add-on features | Universal-3 Pro Streaming | Universal-Streaming |
|---|---|---|
Keyterms Prompting Identify a wide range of entities that are spoken in your audio files, such as person and company names, email addresses, dates, and locations. Provide up to 100 words or phrases (maximum 6 words per phrase) to improve transcription accuracy. | Included | $0.04/hr |
Speaker Diarization Identify a wide range of entities that are spoken in your audio files, such as person and company names, email addresses, dates, and locations. Detect multiple speakers in audio files and segment the transcript into utterances, showing what each speaker said. | $0.12/hr | $0.12/hr |
Control transcription behavior with plain language instructions: provide context, tag audio events, and more. | $0.05/hr | Not supported |
Medical Mode Identify a wide range of entities that are spoken in your audio files, such as person and company names, email addresses, dates, and locations. New Optimize transcription for medical terminology and healthcare conversations with significantly improved accuracy. | $0.15/hr | $0.15/hr |
Ready to start building with voice data?
Speech Understanding
Models | Pay as you go | Custom |
|---|---|---|
Speaker Identification Speaker Identification allows you to identify speakers by their actual names or roles, transforming generic labels like “Speaker A” or “Speaker B” into meaningful identifiers that you provide. Identify speakers by their actual names or roles | $0.02/hr | |
Translation The Translation feature automatically converts your transcribed audio content from one language to another, enabling you to reach global audiences without manual translation work. Convert your content from one language to another | $0.06/hr | |
Custom Formatting The Custom Formatting feature automatically standardizes and formats specific types of information in your transcripts, ensuring consistency across dates, phone numbers, emails, and other data types. Standardize and format specific types of information | $0.03/hr | |
Entity Detection Identify a wide range of entities that are spoken in your audio files, such as person and company names, email addresses, dates, and locations. Identify entities that are spoken, such as names or email addresses | $0.08/hr | |
Sentiment Analysis With Sentiment Analysis, AssemblyAI can detect the sentiment of each sentence of speech spoken in your audio files. Detect the sentiment of each sentence spoken | $0.02/hr | |
Auto Chapters Automatically generate a summary over time for audio and video files. Generate a summary over time for audio and video files | $0.08/hr | |
Key Phrases 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 significant words and phrases | $0.01/hr | |
Topic Detection 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. Label the topics spoken in standardized IAB taxonomy | $0.15/hr | |
Summarization Leverage our AI-powered Summarization models to automatically summarize audio/video data in your products at scale. Customize the summary types to best fit your use case. Generate a summary of audio files at scale | $0.03/hr | |
Guardrails
Models | Pay as you go | Custom |
|---|---|---|
Profanity Filtering Automatically filter out profanity from your transcripts. Filter out profanity from your transcripts | $0.01/hr | |
PII Audio Redaction Identify and remove Personally Identifiable Information, such as phone numbers and social security numbers, from the audio file before it is returned to you. Identify and remove PII from the audio file before it is returned to you | $0.05/hr | |
PII Text Redaction Identify and remove Personally Identifiable Information, such as phone numbers and social security numbers, from the transcription text before it is returned to you. Identify and remove PII from the transcription text before it is returned to you | $0.08/hr | |
Content Moderation Detect sensitive content in your audio and video files - such as hate speech, violence, sensitive social issues, alcohol, drugs, and more. Detect sensitive content in your audio and video files | $0.15/hr | |
Building for healthcare or finance?
LLM Gateway
Models | Input | Output | Custom |
|---|---|---|---|
GPT-5.2 Model with superior performance on complex reasoning tasks, advanced creative work, and sophisticated problem-solving. | $1.75 / 1M | $14.00 / 1M | Get custom rate limits, enhanced concurrency, and enterprise-grade flexibility tailored to your AI workloads |
GPT-5.1 Model with superior performance on complex reasoning tasks, advanced creative work, and sophisticated problem-solving. | $1.25 / 1M | $10.00 / 1M | |
Claude 4.6 Sonnet Model with superior performance on complex reasoning tasks, advanced creative work, and sophisticated problem-solving. | $3.00 / 1M | $15.00 / 1M | |
Claude 4.5 Sonnet Model with superior performance on complex reasoning tasks, advanced creative work, and sophisticated problem-solving. | $3.00 / 1M | $15.00 / 1M | |
Gemini 3 Pro Model with superior performance on complex reasoning tasks, advanced creative work, and sophisticated problem-solving. | $2.00 / 1M | $12.00 / 1M |
Models | Input | Output | Custom |
|---|---|---|---|
GPT-5.2 Model with superior performance on complex reasoning tasks, advanced creative work, and sophisticated problem-solving. | $1.75 / 1M | $14.00 / 1M | Get custom rate limits, enhanced concurrency, and enterprise-grade flexibility tailored to your AI workloads |
GPT-5.1 Model with superior performance on complex reasoning tasks, advanced creative work, and sophisticated problem-solving. | $1.25 / 1M | $10.00 / 1M | |
GPT-5 Model with superior performance on complex reasoning tasks, advanced creative work, and sophisticated problem-solving. | $1.25 / 1M | $10.00 / 1M | |
GPT-5-Mini Model with superior performance on complex reasoning tasks, advanced creative work, and sophisticated problem-solving. | $0.25 / 1M | $2.00 / 1M | |
GPT-5 Nano Model with superior performance on complex reasoning tasks, advanced creative work, and sophisticated problem-solving. | $0.05 / 1M | $0.40 / 1M | |
GPT 4.1 Model with superior performance on complex reasoning tasks, advanced creative work, and sophisticated problem-solving. | $2.00 / 1M | $8.00 / 1M | |
gpt-oss-20b Model with superior performance on complex reasoning tasks, advanced creative work, and sophisticated problem-solving. | $0.07 / 1M | $0.30 / 1M | |
gpt-oss-120b Model with superior performance on complex reasoning tasks, advanced creative work, and sophisticated problem-solving. | $0.15 / 1M | $0.60 / 1M | |
ChatGPT-4o Model with superior performance on complex reasoning tasks, advanced creative work, and sophisticated problem-solving. | $5.00 / 1M | $15.00 / 1M |
Models | Input | Output | Custom |
|---|---|---|---|
Claude 4.6 Sonnet Model with superior performance on complex reasoning tasks, advanced creative work, and sophisticated problem-solving. | $3.00 / 1M | $15.00 / 1M | |
Claude 4.5 Sonnet Model with superior performance on complex reasoning tasks, advanced creative work, and sophisticated problem-solving. | $3.00 / 1M | $15.00 / 1M | |
Claude 4.5 Haiku Model with superior performance on complex reasoning tasks, advanced creative work, and sophisticated problem-solving. | $1.00 / 1M | $5.00 / 1M | |
Claude 4 Sonnet Model with superior performance on complex reasoning tasks, advanced creative work, and sophisticated problem-solving. | $3.00 / 1M | $15.00 / 1M | |
Claude 4.6 Opus Model with superior performance on complex reasoning tasks, advanced creative work, and sophisticated problem-solving. | $5.00 / 1M | $25.00 / 1M | |
Claude 4.5 Opus Model with superior performance on complex reasoning tasks, advanced creative work, and sophisticated problem-solving. | $5.00 / 1M | $25.00 / 1M | |
Claude 4 Opus Model with superior performance on complex reasoning tasks, advanced creative work, and sophisticated problem-solving. | $15.00 / 1M | $75.00 / 1M | |
Claude 3.5 Haiku Model with superior performance on complex reasoning tasks, advanced creative work, and sophisticated problem-solving. | $0.80 / 1M | $4.00 / 1M | |
Claude 3 Haiku Model with superior performance on complex reasoning tasks, advanced creative work, and sophisticated problem-solving. | $0.25 / 1M | $1.25 / 1M |
Models | Input | Output | Custom |
|---|---|---|---|
Gemini 3 Pro Model with superior performance on complex reasoning tasks, advanced creative work, and sophisticated problem-solving. | $2.00 / 1M | $12.00 / 1M | Get custom rate limits, enhanced concurrency, and enterprise-grade flexibility tailored to your AI workloads |
Gemini 3 Flash Model with superior performance on complex reasoning tasks, advanced creative work, and sophisticated problem-solving. | $0.50 / 1M | $3.00 / 1M | |
Gemini 2.5 Flash Model with superior performance on complex reasoning tasks, advanced creative work, and sophisticated problem-solving. | $0.30 / 1M | $2.50 / 1M | |
Gemini 2.5 Flash Lite Model with superior performance on complex reasoning tasks, advanced creative work, and sophisticated problem-solving. | $0.10 / 1M | $0.40 / 1M | |
Gemini 2.5 Pro Model with superior performance on complex reasoning tasks, advanced creative work, and sophisticated problem-solving. | $1.25 / 1M | $10.00 / 1M |
Models | Input | Output | Custom |
|---|---|---|---|
Qwen3 Next 80B A3B Model with superior performance on complex reasoning tasks, advanced creative work, and sophisticated problem-solving. | $0.15 / 1M | $1.20 / 1M | |
Qwen3 32B Model with superior performance on complex reasoning tasks, advanced creative work, and sophisticated problem-solving. | $0.15 / 1M | $0.60 / 1M | |
Kimi K2.5 Model with superior performance on complex reasoning tasks, advanced creative work, and sophisticated problem-solving. | $0.60 / 1M | $3.00 / 1M |