Generates realistic text-to-speech and speech-to-text audio using AI voice models. Connect Fish Audio to AI agents, automate workflows, and scale with confidence.
Start from Fish Audio’s Create Speech to Text step and wire it straight into the run — one node on the canvas, no glue script.
Add Make an API Call as the next step, then branch, filter or hand off to the rest of your stack. The whole path stays on one canvas your team can read.
Fish Audio brings 3 ready-made steps for AI work, and every run records what went in and what came back.
Fish Audio workflow on the canvas: Create Speech to Text then Make an API Call
Everything you need to know about connecting Fish Audio to your workflows.
