---
title: "Fish Audio integration for LuumenAI"
url: "https://www.luumen.ai/integrations/fish-audio/"
entity: SoftwareIntegration
category: "AI & automation"
audience: "SRE, DevOps, platform engineering, IT operations"
---

# Fish Audio integration for LuumenAI

Read voice models, agents, and credit. Change agent config as an approved step.

## What LuumenAI can do with Fish Audio

LuumenAI connects to Fish Audio with an API token and exposes 10 tools (6 read-only · 3 write · 1 destructive). For connected tools, admins configure which actions may run automatically and which require approval, within the access granted to the user.

## Key facts

- Authentication: API token
- Tools available: 10 tools (6 read-only · 3 write · 1 destructive)
- Deployment: scoped as part of your Pilot, Platform, or Managed rollout
- Category: AI & automation

## About Fish Audio with LuumenAI

Connect Fish Audio with an API key and Luumen can read your workspace directly: which voice models are trained and usable, how your agents are configured, what sessions they have handled, and how much package allowance and paid credit remain. Changes — creating an agent, updating its draft prompt or voice, synthesizing speech — are previewed first and go through approval before they run.

## Example tools

Read-only (6 in total):

- `FISH_AUDIO_GET_ACCOUNT_BALANCE` — Return the connected Fish Audio account's package allowance and API credit so an agent can distinguish free quota from paid credit.
- `FISH_AUDIO_GET_AGENT` — Return an agent's workspace metadata together with its current draft conversation configuration.
- `FISH_AUDIO_GET_VOICE_MODEL` — Get a Fish Audio voice model by ID and inspect whether it is trained and suitable for synthesis.
- `FISH_AUDIO_LIST_AGENTS` — Search agents in the connected Fish Audio workspace, including draft or archived agents when requested.
- `FISH_AUDIO_LIST_AGENT_SESSIONS` — List conversation sessions for the workspace or a specific agent, filtered by lifecycle status, caller, or creation time.
- `FISH_AUDIO_LIST_VOICE_MODELS` — Search public or workspace-owned Fish Audio voice models.

Write and destructive (4 in total, subject to configured approval policy):

- `FISH_AUDIO_CONFIGURE_AGENT` — Partially update an agent's draft prompt, voice, and core conversation behavior without publishing it.
- `FISH_AUDIO_CREATE_AGENT` — Create a private Fish Audio agent, optionally with an initial prompt, voice, and core conversation settings.
- `FISH_AUDIO_DELETE_AGENT` — Permanently delete a Fish Audio agent by ID; use only when deletion is explicitly intended.
- `FISH_AUDIO_SYNTHESIZE_SPEECH` — Generate downloadable speech with Fish Audio's free S2.1 model using one or more discovered voice model IDs.

## Frequently asked questions

### How does LuumenAI connect to Fish Audio?

Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.

### Can LuumenAI change things in Fish Audio on its own?

For connected tools, admins configure which actions may run automatically and which require approval, within the access granted to the user.

### Is there an audit trail?

Every call to Fish Audio — read or write, approved or declined — is recorded with the actor, the input, and the result.

Full page: https://www.luumen.ai/integrations/fish-audio/