AssemblyAI for AI agents
Speech-to-text and audio intelligence API.
What your agent can do with AssemblyAI
AssemblyAI: speech-to-text and audio intelligence API. Through AMXP your agent calls it like any other tool: no AssemblyAI account, no separate API key and no extra subscription. The call is priced up front and paid from your AMXP balance.
AssemblyAI is on the AMXP roadmap and not callable yet. Everything on this page describes how it will work once its connector ships.
How to call it
The same three calls work for every provider. Your agent does this on its own once AMXP is installed.
// Find the right AssemblyAI endpoint, check its price, then run it.
const [tool] = await amxp.discover({ provider: "assemblyai" })
const spec = await amxp.inspect(tool.id) // parameters, price per call
const result = await amxp.execute(tool.id, { /* params from spec */ })What AssemblyAI charges
$0.15/hr (Universal-2 / Universal-Streaming); $0.21/hr Universal-3.5 Pro; $15 per 1M chars TTS
- Model
- Pay as you go
- Currency
- USD
- Free tier
- Yes
Up to 185 hrs pre-recorded + 333 hrs streaming transcription; no credit card
Prices as of 2026-11-02, source: https://assemblyai.com/pricing.
Pricing through AMXP
0% markup, pay per call. Your agent sees AssemblyAI's own price from amxp.inspect() before it runs anything, the amount is reserved from your balance, and only the real cost is settled. No monthly fee, no AssemblyAI account. How pricing works
Alternatives in Speech & Voice
Your agent can compare these by fit and price with amxp.discover() and pick per task.
- CartesiaLow-latency TTS, STT and voice agents.
- DeepgramSpeech-to-text and text-to-speech APIs.
- ElevenLabsText to speech and voice cloning.
- Fish AudioText to speech and voice cloning.
- GladiaAsync and realtime transcription API.
- Inworld TTSExpressive text-to-speech API.
- Rev.aiSpeech-to-text API from Rev.
- SonioxSpeech-to-text in many languages.
- SpeechmaticsMultilingual speech-to-text API.
