Fish Audio Review (2026): Drama 3 Pricing and Testing Limits

Updated October 13, 2026 with sourced Drama 3 launch information. The historical hands-on demo check was August 28, 2026. Kingy has not run a hands-on Drama 3 test, self-hosted the weights or completed an ElevenLabs comparison. Paid API use, export fidelity and cancellation remain untested.

Buying details checked October 22, 2026: Fish Audio buying profile: Credits reset monthly and minutes are estimates. The first-month discount is temporary. A celebrity-voice demo does not establish permission to reuse that voice. The demonstration and older product/version details below keep their original dates.

Disclosure: Kingy did not purchase credits or a subscription for this update. No affiliate relationship affected the verdict.

What Kingy has verified

The August demo exposed a testing limit. One 200-character English test with the Sarah demo voice generated and played in roughly 15.6 seconds. Choosing Adrian reset our text to Fish Audio’s sample script, and a later attempt to regenerate the same controlled script reached the anonymous demo limit and opened a sign-in prompt. No paid credit was used. No download control was visible in that anonymous flow.

That leaves quality, export fidelity and production credit burn unproven. This review publishes the method and empty scorecard rather than inventing results.

Drama 3 launch: access and editing limits

Fish Audio’s October 13, 2026 launch announcement expands the earlier Drama 3 preview to text-to-speech on the web, the iOS and Android apps, and the API. Fish Audio positions the model around emotional direction for dialogue and narration; those performance claims have not been tested by Kingy.

The Drama 3 documentation lists drama-3 as the released API model and drama-3-preview separately. Record the exact model used in any comparison.

Interactive audio editing and audio inpainting remain in small, invite-only testing. Fish Audio says an editing API is coming later; it is not part of the generally available launch. A public workflow should budget for changing direction and regenerating takes.

Drama 3 weights and commercial self-hosting

Fish Audio has announced Drama 3 weights under the restricted Fish Audio Community License v1.0. These are open weights with conditions, and should not be presented as unrestricted open source.

The community commercial allowance requires your and your affiliates’ combined gross revenue, from all sources over the preceding 12 months, to be below US$500,000. Deploying the model for a particular client also requires checking that client’s eligibility. A hosted speech-generation or voice-cloning service requires a separate written licence regardless of revenue, subject to the licence’s defined exceptions. Producing finished audio for clients is treated differently from giving them self-service generation access. Check eligibility, attribution requirements and transition terms before commercial self-hosting. This licence does not replace the terms for Fish Audio’s hosted plans or the separate S2 weights licence.

Proposed video test: Drama 3 vs ElevenLabs

The proposed video angle is “Drama 3 vs ElevenLabs: the same emotional dialogue, measured cost and editing effort.” No hands-on comparison has been run, and there is no winner or measured cost result.

Use voices whose speakers have given written consent for cloning, testing and publication on both services. Give each system the same spoken dialogue, reference recordings and intended emotion. Adapt control syntax as needed, retain both prompts, and record each model version, settings and plan. Blind the listening order and set acceptance criteria before generating takes.

Publish the raw takes, listener scores and usage receipts. Count only tools accessible in the tested plan; invite-only Drama 3 editing cannot be assumed to reduce editing time in a public comparison.

Quick verdict

Best for: developers who can test via API, creators with clear voice consent, and personal experiments using Fish Audio’s free model or public demo.

Skip it if: you need a verified blind quality winner today, expect free outputs to carry commercial rights, need a public fixed-duration retention promise, or want to clone a voice without written permission.

Pros

• The Drama 3 API has a dated introductory offer; the pricing table below separates characters from S2.1 Pro’s UTF-8-byte billing.
• The API has no subscription or minimum-spend requirement in the published pricing documentation.
• Fish Audio publishes explicit consent guidance for voice cloning.

Cons

• The anonymous demo did not support a complete controlled three-voice test.
• Selecting another voice reset the entered script, creating an easy test-design error.
• No export button was visible in the tested anonymous demo.
• Hosted-plan commercial rights and self-hosted-weight licensing need separate checks.
• Published language counts vary across Fish Audio pages, so model-specific support must be checked.
• Drama 3 editing and inpainting are invite-only, with an editing API still to come.

What Fish Audio is

Fish Audio is a speech platform for text-to-speech, voice design, transcription and voice cloning. Its consumer site offers a web workflow and public examples; its developer documentation exposes models through an API.

Those are not interchangeable products. A free web demo can show whether a voice is interesting, but it does not prove API reliability, batch cost, export metadata or commercial rights. Likewise, an API price does not tell you whether a particular voice pronounces a client’s names correctly.

For context beyond one vendor, compare Kingy’s coverage of the open-source Miso One voice model and Nvidia Fugatto.

How Kingy tested Fish Audio on August 28, 2026

The exact test script was:

At 07:45 on February 29, Dr. Siobhán O’Rourke whispered, “The Łódź prototype costs $1,347.56—really?” Then she laughed, steadied herself, and said: We’ll deliver version 2.1 by Thursday.

It deliberately combines time, dates, a title, Irish and Polish names, currency, decimals, quoted speech, an emotional direction and a version number.

Blind voice test: status and method

Result

Incomplete—no winner declared. The Sarah run completed, but the Adrian selection reset the script and a later controlled attempt hit the anonymous demo limit. Comparing different scripts would confound the result, so Kingy did not score naturalness, pronunciation, emotion or pacing.

The companion files fish-audio-blind-test-script.txt and fish-audio-blind-test-scorecard.csv contain the publishable protocol. To complete it, generate the identical script with three voices under the same model and settings, randomize clips A–C, and collect independent scores from at least three listeners before revealing the voices.

What to score

Raw clips, settings and listener-level scores should be published with the article. Averages without the underlying evidence are not enough.

API pricing and true credit burn

The Drama 3 launch offer is US$10 per million characters from October 13 through November 12, 2026, versus a US$50 list price. The S2.1 and other service rates below come from the August 28 check and remain listed in the pricing documentation checked on October 13.

The launch announcement uses characters; the general TTS pricing page uses UTF-8 bytes and does not yet list Drama 3. Keep both units in the test log and confirm Drama 3’s billing meter before estimating multilingual costs. These advertised rates are not Kingy-measured production costs.

Fish Audio estimates one million bytes at roughly 180,000 English words or 12 hours of audio. That is a vendor estimate, not Kingy’s measurement. At the published S2.1 Pro rate, the headline unit cost is attractive; the real project cost still depends on retries, pronunciation repairs, encoding and discarded takes.

A production test should log input characters and UTF-8 bytes, successful and failed requests, returned audio duration and invoice delta. It should report both cost per delivered hour and cost including rejects.

Voice cloning, consent and verification

Fish Audio’s voice-cloning best practices say users should clone only their own voice or one they have permission to use, obtain written permission and avoid public figures without permission. That is the minimum responsible standard, not a paperwork detail.

Fish Audio also describes a professional cloning path with live voiceprint matching and longer reference material. Kingy did not test either instant or professional cloning. Any future review should document who supplied the voice, how consent was captured, whether the reference data can be deleted and how well the system resists a mismatched speaker.

Commercial rights, cancellation and refunds

For the hosted platform, Fish Audio’s terms distinguish free/personal use from paid commercial use. Check the applicable plan before using a hosted output in a sponsored video, client deliverable, advertisement or monetized course. Self-hosted Drama 3 has the separate community-licence conditions described above.

The terms also describe subscriptions as automatically renewing. Cancellation is available through account settings, but fees already paid are generally not prorated or refunded except where the terms or law provide otherwise. Kingy did not purchase, cancel or request a refund, so the ease and timing of that flow remain untested.

Before using an output commercially, save the plan name, generation date, applicable terms and proof of voice consent with the project file.

Privacy and retention

Fish Audio’s privacy policy says content and account data are retained as needed for its systems and legitimate purposes, with deletion rights subject to legal and operational exceptions. It does not give one universal, simple deletion countdown for every kind of content.

Voice data is biometric-adjacent in practical risk even when a policy uses different legal categories. Do not upload a client or employee voice merely because the interface makes cloning easy. Get explicit permission, minimize the recording, avoid unnecessary personal details and confirm deletion controls.

Export fidelity and failure cases

Export fidelity could not be tested because the anonymous demo showed no download control. A complete test should compare WAV and compressed exports, if offered, for duration, sample rate, clipping, leading/trailing silence, metadata and pronunciation. It should also confirm that the downloaded file matches the preview rather than being regenerated.

Observed and credible failure cases include:

• changing voices can reset the script;
• an anonymous demo limit can interrupt a controlled comparison;
• a voice can pronounce ordinary English well but fail names, numbers or code-switching;
• retries can make the real cost higher than the headline API rate;
• a technically good clone may still be unusable because consent or commercial rights are missing;
• Fish Audio pages can describe different language counts, so users should verify the exact model and feature.

Fish Audio FAQ

Is Fish Audio free?

Fish Audio lists a free S2.1 Pro API model and exposes a public demo, but free access does not automatically include commercial rights or unlimited anonymous generations.

How much does Fish Audio cost?

The Drama 3 launch offer is US$10 per million characters through November 12, 2026, versus a US$50 list price. S2.1 Pro remains listed at $15 per million UTF-8 bytes. Consumer plans and allowances should be checked at checkout.

Can I use Fish Audio commercially?

Hosted commercial use depends on the plan and terms. Self-hosted Drama 3 uses the restricted community licence, including a combined-revenue threshold and separate hosted-service rules. Save the applicable terms and voice consent with the project.

Can I clone anyone’s voice?

No. Fish Audio’s own guidance requires ownership or permission and warns against cloning celebrities or public figures without permission.

Did Fish Audio win Kingy’s blind test?

No winner was declared. The anonymous limit prevented a fair controlled comparison, and Kingy will not score unmatched scripts.

Final verdict

Fish Audio’s published API economics are compelling enough to justify a controlled trial. Its August public demo was fast in one run, but it did not provide enough evidence for a quality verdict, export verdict or true cost-per-delivered-minute calculation. Use Fish Audio for permissioned experiments and API prototyping; delay production dependence until the blind clips, reject-adjusted costs and export files have been audited.

Official sources

• Drama 3 launch announcement, October 13, 2026
• Drama 3 documentation and model access
• Drama 3 weights and model card
• Fish Audio Community License v1.0
• Fish Audio pricing and rate limits
• Fish Audio voice-cloning best practices
• Fish Audio terms
• Fish Audio privacy policy