Misc
Miscellaneous sections: architecture diagrams, playground, connectors, and model visualizations.
Review Status
Marketecture
Platform architecture diagram with API product grid. Dark background.
Everything you need to build with Voice AI.
- Transcribe speech with unmatched accuracy
- Understand context, intent, and meaning
- Power agentic workflows in real time
- Scale securely, from MVP to production
Pre-recorded Speech-to-Text API
Get clean, customizable transcripts in 99 languages with industry-leading accuracy and natural language prompting.
Realtime Speech-to-Text API
Stream transcripts in real time with async-level accuracy, so your agent responds fast without mishearing the user.
Voice Agent API
Build production-ready voice agents with built-in turn detection and interruption handling, so you ship fast without the complexity.
Speech Understanding API
Go beyond basic transcription. Extract speaker ID, sentiment, chapters, and summaries from a single API call.
Guardrails
Redact PII and moderate content inline on audio and transcripts, so sensitive data never hits your logs or your LLM.
LLM Gateway
Route between every LLM from one endpoint with built-in fallback, so you swap models and survive outages without touching your code.
Explore the platform
Models, APIs, and infrastructure in one place.
Playground
Platform playground section with heading, body, CTA, and image slot.
Up and running in minutes
The same API handles your first transcript and your millionth. No new SDKs to learn as you grow.
Connectors
Frontier model connectors grid showing supported LLM models.
Every frontier model, one connection
GPT-5.1
GPT-5.2
Claude Sonnet 4.6
Claude Opus 4.6
Claude Haiku 4.5
Gemini 3 Flash
Qwen3-32B
Kimi-K2.5
+ more added continuously
Model Dark
Voice/audio pipeline diagram showing input, Speech API, and use case outputs.
Voice + Audio
Any source / Any format
Conversation Intelligence
Voice Agents
AI Scribe
Agent Assist
AI Notetaker
Captioning
Call Analytics
+ more use cases