Speech to text API for AI agents

Scrollport gives AI agents one tool to transcribe audio and video, Scribe Speech-to-Text from ElevenLabs, through one MCP, CLI or HTTP connection. It costs $0.0052 per minute, paid per use from one prepaid wallet with no subscription, provider accounts or API keys.

Updated

What does Scrollport's Speech to text API return?

Transcribe audio or video with word timestamps and optional speaker labels.

Scribe Speech-to-Text

by ElevenLabs$0.0052 per minute

You ask your agent

“Transcribe my one-minute audio clip and label the speakers.”

You get

Text
Welcome to Scrollport. Our product meeting is in London on Monday. Alex will present the new research tools, and the…
Entities
Scrollport, London, Monday and 2 more
Language code
eng
Duration (seconds)
8
Language probability
0.955

Use it with your agent

Copy the prompt and paste it into your agent, then tell it what you need.

Read https://scrollport.com/start. Use my existing Scrollport connection, or help me connect if needed. Then help me transcribe audio and video with Scrollport's Speech to text API tools. Start with Scribe Speech-to-Text (tool ID: elevenlabs.scribe-speech-to-text) unless another Scrollport tool fits my request better. Ask me for the details you need, then show me the result.

Provider access is included. If your agent isn't connected to Scrollport yet, it will help you set that up.

Questions about Speech to text API

Is there a free Speech to text API?

Scrollport has no free tier: this tool costs $0.0052 per minute, paid per use from a prepaid wallet with no subscription. Connecting your first agent adds $1 of trial credit, so you can try a tool before adding funds.

How do I use a Speech to text API with an AI agent?

Connect your agent to Scrollport once, over MCP, the Scrollport CLI or the HTTP API. Then ask it to transcribe audio and video: it finds the tool on this page, checks its inputs and price, runs it and returns the result, with no provider API key to manage.