Voice (speech-to-text for AI agents
4 APIs compared on price, free tier, MCP support and real usage. Prices from the vendors' pricing pages, checked Oct 9, 2026.
Free to start
4 of 4
ElevenLabs, Deepgram, AssemblyAI
Official MCP server
4 of 4
plug straight into Claude Code, Cursor and others
| API | Free | Price | SDK downloads / wk | GitHub stars | MCP |
|---|---|---|---|---|---|
| ElevenLabs Text-to-speech, speech-to-text (Scribe), voice cloning and conversational voice-agent APIs. |
Free plan: 10,000 TTS characters/month (v4) | Free plan · paid from $6/mo | 3.2M | 3,135 | MCP |
| Deepgram Real-time and batch speech-to-text, text-to-speech and voice-agent APIs. |
$200 credit, no credit card | Free plan then Nova-3 streaming $0.0048/min (promo; regular $0.0077);... |
1.7M | 469 | MCP |
| AssemblyAI Speech-to-text API (batch and streaming) with diarization, speech understanding and voice agents. |
Up to 185 hours pre-recorded and 333 hours... | Free plan then Universal-2 $0.15/hour; Universal-3.5 Pro $0.21/hour;... |
1.3M | 213 | MCP |
| Cartesia Low-latency text-to-speech (Sonic), speech-to-text (Ink) and managed voice agents. |
20K credits/month + $1 prepaid for agents | Free plan · paid from $5/mo | 286K | 134 | MCP |
Other categories
Web search APIs Scraping and crawling Browser automation (cloud) Code sandboxes Memory for agents Vector databases LLM gateways and routers Email sending Payments for agents Blockchain RPC and node providers DEX swap and liquidity APIs Crypto market and on-chain data 3D model generation Image generation APIs Sound effects and music generation Video generation APIs