customers
All customer stories
Top Voice AI companies are building with Assembly.
resources
Latest Release
Text-to-Speech API
Our first text-to-speech model, AssemblyAI-TTS-1, is built for voice agents, on live calls. It sounds natural, responds fast, and keeps callers on the line.
resources
AssemblyAI-TTS-1
01
Production infrastructure that scales with you
02
The most accurate models built on cutting-edge research
03
Endpoints for every kind of build
04
Built for what you’re building
05
Configurable outputs for any transcript
Pre-recorded Speech-to-Text API Transcribe audio and video files with speaker labels and formatting. 
Realtime Speech-to-Text API Stream audio in and get transcripts back as people speak. 
Sync Speech-to-Text API Send a short clip and get finished text in the same request. 
Speech Understanding API Summaries, sentiment, entities and more, built on your transcripts. 
Guardrails Detect and redact PII and unsafe content in voice data. 
Text-to-Speech API New Natural, low-latency text-to-speech built for voice agents. 
LLM Gateway Open and frontier LLMs that perform best on voice tasks. 
Dictation API Add dictation anywhere your users type. 
Voice Agents Speech-to-text and text-to-speech tuned for live calls. 
Meeting Notetakers Accurate transcripts and summaries for every meeting. 
Agent Assist Real-time guidance for human agents on live calls. 
Medical Transcription Clinical-grade accuracy for drugs, dosages and procedures. 
Dictation Turn spoken drafts into clean written text. 
AI Scribes Ambient clinical notes from patient conversations. 
Medical mode Clinical vocabulary for drugs, dosages and procedures. 
Veterinarian mode Soon Terminology tuned for veterinary care. 
Legal mode Soon Precision for proceedings, depositions and contracts. Voice AI infrastructure loved by startups and enterprises
