customers
All customer stories
Top Voice AI companies are building with Assembly.
resources
Latest Release
Universal 3.5 Pro
Our new flagship speech-to-text model handles real-world audio the way it actually happens. Available for real-time and pre-recorded audio.
resources
The people your voice agent serves speak dozens of languages — and many move between them mid-sentence. Reaching a global user base means understanding each caller in their own language, handling code-switching naturally, and holding accuracy on the names and numbers that matter in every one. Here's the full landscape across AssemblyAI's streaming models.
Language coverage
Only need your core markets? Universal-Streaming Multilingual covers 6 at lower cost.
Flagship languages
18
Flagship accuracy with native code-switching on Universal-3.5 Pro Streaming and the Voice Agent API.
Source: Voice Agent API
Code-switching
Native
Mid-sentence language switching — Hinglish, Spanglish, and more — without a declared primary language.
Source: Realtime STT
Cost-optimized
6
Universal-Streaming Multilingual covers English, Spanish, German, French, Portuguese, and Italian at lower cost.
Source: Realtime STT
Bring your own
$0.45/hr
Universal-3.5 Pro Realtime, all 18 languages, for teams running their own stack.
Source: Pricing
Customer story · Report 5
“We were searching for the best realtime ASR model for our voice agent pipeline in Fireflies. The new Universal-3.5 Pro speech model from Assembly is best so far in terms of accuracy, latency and language switching.”
— Foysal Osmany, Software Engineer at Fireflies
The challenge
Multilingual voice agents face compounding challenges: dialect variation within a language, code-switching mid-sentence, proper nouns that fit no single language model, and the need to keep accuracy in every language. Most providers force a tradeoff — a handful of languages with great accuracy, or a hundred with mediocre accuracy. The gap is false confidence: handling simple Spanish phrases in a demo doesn't mean handling a bilingual support call that switches between Spanish and English.
Recommended
18 languages, fully managed
$4.50 /hr
Flat rate regardless of language
Bring your own stack
Same 18 languages, your stack
$0.45 /hr
Transcription only
Cost-optimized
6 core languages, per turn
Lower cost
English, Spanish, German, French, Portuguese, Italian
Need English only? Universal-Streaming English is the lowest-cost option.
Code-switching
The model recognizes and preserves language switches mid-utterance, so bilingual calls flow naturally — no primary language to declare, and prompting handles the proper nouns and technical terms that span languages.
Live transcript
English → French
I said something like, “J'ai dit à mes étudiants que it's time to really pay attention to what the idea of code-switching is.”
English → Hindi
हम छह साल की उम्र में मिले थे, but I have an exam to give tomorrow.
English → Mandarin
But this sentence, 我让你干工作了 — you can see the tone at the end tells you the situation is different from before.
Architecture patterns
Three ways to structure a multilingual deployment, from a single-market launch to premium multi-market accuracy to a cost-optimized core-market build — all on the same AssemblyAI foundation.
Voice Agent API in one of the 18 supported languages. Ship in an afternoon, expand later.
Voice Agent APIUniversal-3.5 Pro Realtime across 18 languages in a cascading stack, with full control over LLM and TTS per market.
Universal-3.5 Pro RealtimeUniversal-Streaming Multilingual for English, Spanish, German, French, Portuguese, and Italian at lower cost — upgrade to Universal-3.5 Pro for the full 18 and native code-switching.
Universal-Streaming MultilingualGet your API key and build in your primary markets today — scale across all 18 languages without switching providers.
AssemblyAI supports 18 languages at flagship accuracy on Universal-3.5 Pro Streaming and the Voice Agent API, with native mid-sentence code-switching. For core European and English markets on a tighter budget, Universal-Streaming Multilingual covers 6 languages at lower cost, and Universal-Streaming English is the lowest-cost English-only tier. Premium accuracy plus cost-optimized options on one account is what sets it apart for multilingual voice agents.
For your primary markets, use the Voice Agent API or Universal-3.5 Pro Realtime across the 18 flagship languages — code-switching is handled natively, with no primary language to declare. If you only serve English, Spanish, German, French, Portuguese, or Italian and want lower cost, use Universal-Streaming Multilingual. No separate pipeline per language, and no provider switch as you expand.
18 at flagship accuracy on Universal-3.5 Pro Streaming: English, Spanish, French, German, Italian, Portuguese, Arabic, Danish, Dutch, Hebrew, Hindi, Japanese, Mandarin, Vietnamese, Finnish, Norwegian, Swedish, and Turkish — with native code-switching. A lower-cost Universal-Streaming Multilingual model covers English, Spanish, German, French, Portuguese, and Italian; Universal-Streaming English handles English-only. For non-real-time use like post-call analytics, pre-recorded transcription adds automatic language detection across 99+ languages.
Yes — natively. Universal-3.5 Pro Streaming recognizes and preserves language switches mid-utterance (Hinglish, Spanglish, and more) without requiring you to declare a primary language. Prompting handles the proper nouns and technical terms that span languages.
For live streaming you don't declare a language — Universal-3.5 Pro Streaming handles code-switching across its 18 languages automatically, and you select the model with the speech_model parameter (for example, universal-3-5-pro, or universal-streaming-multilingual for the 6-language cost-optimized tier). For pre-recorded audio, automatic language detection identifies the dominant language and routes to the best model across 99+ languages.
There's no language surcharge on the flagship models. The Voice Agent API is a flat $4.50/hr regardless of language; Universal-3.5 Pro Realtime is $0.45/hr for transcription only. Universal-Streaming Multilingual is a lower-cost option for the 6 core languages, and Universal-Streaming English is the lowest-cost English-only tier.
