Skip to main content
Fish Agents is a hosted platform for real-time voice agents. Define an agent’s prompt, voice, knowledge, and tools in the Builder console, publish it, and talk to it — from your web app through the SDK, over a phone number, or anywhere the REST API reaches. Speech recognition, turn-taking, and speech synthesis are handled for you.

Quickstart

Create an agent and have your first conversation in minutes.

Concepts

Agents, drafts, versions, sessions — the mental model.

Integration overview

Pick the right surface for your app.

Three surfaces, one agent

All three operate on the same agents. The core console workflow — creating agents, editing configuration, publishing versions — is also available over the API with your standard Fish Audio API key:

From draft to production

1

Configure

Write the system prompt, set the first message, and pick a voice and speaking language. Attach knowledge sources and tools. Edits save to the agent’s draft automatically.
2

Test

Talk to the draft in a preview call, or run scripted agent tests that judge each reply pass or fail.
3

Publish

Publishing freezes the draft into an immutable, numbered version. Live sessions always run the published configuration, so you can keep editing safely.
4

Integrate

Drop the web SDK into your app, create sessions over REST, or bind a phone number so the agent answers inbound calls.
5

Monitor

Review transcripts, tool calls, and recordings in conversation history, let post-call analysis summarize and evaluate every call, and push results to your backend with webhooks.

Capabilities

Prompt & voice

System prompt, first message, and any voice from the Fish Audio Voice Library.

Knowledge base

Upload documents the agent retrieves from during conversations. Update a source and every agent using it picks up the new content.

Tools

Call your backend with webhook tools, run code in your app with client tools, and toggle built-in system tools.

Dynamic variables

Personalize each session with values injected at call time.

Versions & publishing

Draft safely, publish deliberately, and read back the full version history.

Telephony

Answer inbound calls on phone numbers bound to your agents.

Conversation history

Transcripts, tool timelines, and per-speaker recordings — you choose what each agent stores.

Post-call analysis & webhooks

Automatic summaries, structured data extraction, and success criteria — delivered to your systems via webhooks.