# AssemblyAI — card for AI agents

Speech-to-text API (batch and streaming) with diarization, speech understanding and voice agents.

Maker: AssemblyAI · category: Speech-to-text and transcription

## Price (official page)
- Free tier: Up to 185 hours pre-recorded and 333 hours streaming transcription, no credit card
- Usage price: Universal-2 $0.15/hour; Universal-3.5 Pro $0.21/hour; Universal-Streaming $0.15/hour; diarization +$0.02/hour
- Per minute: STT: Universal-Streaming $0.15/hour = $0.0025/min (AgentGid conversion from the listed price)
- Pricing page: https://www.assemblyai.com/pricing (checked 2026-10-09)
- Note: Pay as you go, no subscription; custom enterprise rates. The official MCP server is a docs-lookup server only (searches AssemblyAI documentation), not an API-calling server. Voice Agent API $4.50/hour.

## Connect
- Official MCP server: https://assemblyai.com/docs/mcp
- npm: `npm install assemblyai`
- PyPI: `pip install assemblyai`
- Repository: https://github.com/AssemblyAI/assemblyai-python-sdk
- Status: All Systems Operational

## Other APIs in this category
- Groq Speech-to-Text (Whisper): https://agentgid.com/apis/groq-speech/agent.md
- faster-whisper: https://agentgid.com/apis/faster-whisper/agent.md
- ElevenLabs: https://agentgid.com/apis/elevenlabs/agent.md
- Whisper (self-hosted): https://agentgid.com/apis/whisper/agent.md
- Deepgram: https://agentgid.com/apis/deepgram/agent.md

## Links
- AgentGid page: https://agentgid.com/apis/assemblyai/

---
AgentGid's catalog is curated: every entry was checked against the maker's official pages (registry, repository, license and pricing pages) on the date shown; a license value shows the quote it stands on wherever AgentGid has one. Usage numbers come from AgentGid's own scan of public repositories set up for AI coding agents. Claims by makers are reported, not tested by AgentGid.