Expressive AI voice platform

How to use
Fish Audio.

Creating expressive narration and dialogue, localizing approved scripts, prototyping realtime speech, and integrating controlled text-to-speech or authorized voice models into products.

Open Fish Audio ↗ Official download ↗
What it isAI voice platform and API for expressive text-to-speech, realtime streaming, multi-speaker dialogue, and consented voice cloning Workflows2 UpdatedJuly 2026

Fish Audio is a AI voice platform and API for expressive text-to-speech, realtime streaming, multi-speaker dialogue, and consented voice cloning. Creating expressive narration and dialogue, localizing approved scripts, prototyping realtime speech, and integrating controlled text-to-speech or authorized voice models into products. This guide covers the whole path in one place: official access, a first session that produces something reviewable, the checks that make output trustworthy, and the permissions worth limiting before you connect real work.

Troiana principle

AI should make the work easier to inspect. If the workflow removes the source, the owner, or the review step, redesign the workflow.

01

Access & setup

Find, install, and sign in to Fish Audio

Get into the official Fish Audio experience with the right account and a setup you understand.

  1. 01

    Start at https://fish.audio/ and confirm the domain before entering account or payment information.

  2. 02

    Availability: Fish Audio is available through its official web application, HTTPS API, Python and JavaScript SDKs, and WebSocket streaming interfaces.

  3. 03

    An official fish.audio account or server-side API key, rights and documented consent for every reference voice and script, a suitable plan or model license, secure audio storage, and human audio review.

  4. 04

    Sign in with the account you intend to keep using, then review plan, data, notification, and permission settings.

  5. 05

    Run one low-risk test task before connecting sensitive files, repositories, or workspace data.

  • Use official download pages.
  • Review permissions during setup.
  • Keep installers and applications updated.
02

First session

Your first useful Fish Audio session

Learn the interaction loop using a small task with a clear outcome.

  1. 01

    Define the audience, script owner, speaker identity, language, pronunciation, emotion, pace, disclosure, distribution, retention, and approval criteria.

  2. 02

    Use a stock or explicitly consented voice, prepare a clean approved script, and generate a short low-cost sample before cloning, streaming, or processing a full production.

  3. 03

    Review every word, name, number, pause, emotion, identity cue, artifact, loudness, and whether the result could imply a false endorsement or authentic recording.

  4. 04

    Revise text and prosody, master audio externally, obtain speaker and content-owner approval, attach synthetic-voice disclosure, and archive consent, settings, and final provenance.

  • State the outcome before the background.
  • Provide the real source material.
  • Review the result before expanding the task.
03

Quality control

Check the quality of Fish Audio output

Turn a promising generation into an asset you can legally and safely ship.

  1. 01

    Restate the brief, the deliverable format, and where the asset will appear before judging any output.

  2. 02

    Inspect at full resolution: generated media hides its errors at thumbnail size.

  3. 03

    Check the details these systems reliably get wrong — hands, text, logos, reflections, symmetry, and edge artefacts.

  4. 04

    Confirm the licence and commercial-use terms for your plan, and check the output does not reproduce a recognisable style, mark, or likeness you have no right to use.

  5. 05

    Review for accessibility and delivery: alt text, contrast, colour profile, file size, and the exact export format.

  • Inspect at full resolution before approving anything.
  • Confirm commercial-use rights before an asset reaches a client.
  • Keep the prompt and settings with the asset so it can be reproduced.
04

Privacy & permissions

Use Fish Audio safely

Use the platform without surrendering rights, likenesses, or client material you do not control.

  1. 01

    Confirm you hold the rights to every reference image, voice, or clip before uploading it.

  2. 02

    Check whether your plan trains on submitted content, and opt out before uploading client work.

  3. 03

    Never upload a real person's likeness or voice without their explicit, documented consent.

  4. 04

    Review the output for marks, styles, or likenesses you have no licence to reproduce.

  5. 05

    Label synthetic media where your client, platform, or jurisdiction requires disclosure.

  • A few seconds of reference audio can reproduce a recognizable voice, creating impersonation, fraud, harassment, and false-endorsement risk. Use only the official fish.audio service, verify current model and commercial license, obtain specific documented consent, prohibit deceptive use, and never clone minors or unaware speakers. Keep keys server-side, minimize retained audio, review pronunciation and meaning, disclose synthetic speech, and provide a fast abuse-removal path.
  • Follow your organisation's approved-use policy.
  • Never treat fluent output as authorization to act.
05

Core workflows

Step-by-step ways to use Fish Audio for the work it does best.

Each workflow is a separate guide with its own steps and review checkpoints.

01 WorkflowProduce an approved narration with Fish Audio

Turn a locked script and authorized voice into expressive narration without obscuring synthetic origin or speaker approval.

 02 WorkflowOperate a consent-gated Fish Audio TTS API

Integrate speech and streaming with server-side keys, voice authorization, bounded jobs, abuse prevention, and human release control.

06

Official references

Check the current product documentation.

Features, plan limits, availability, and data controls change. These official pages are the starting points used for this guide.

Explore the Troiana AI Hub →