50% off yearly plansLimited time — ends in 50% off yearly plans · ends in

Fish Audio S2 Pro AdAnt · by Fish Audio

Fish Audio S2 Pro AI Voice Generator

S2 Pro is Fish Audio's expressive text-to-speech model before Drama 3: it takes bracketed directions too, with a calmer read.

  • Bracketed directions
  • Fish Audio voice library
  • $0.015 per 1k characters
Made with Fish Audio S2 Pro“[barely holding it together, forcing a smile] I'm fine. Really. [shaky breath] [voice breaking] I just thought you'd at least call.” · Fish Audio S2 Pro, one take

Same script, every voice model: a UGC voiceover

We ran this script once on each model, with no retries and no edits: a warm, friendly woman in her late twenties, casual like a creator talking to a friend: described on MiniMax, and the preset voices Sarah on Fish Audio and Jessica on ElevenLabs. Whether it sounds like a person talking rather than reading, and where it pauses.

Okay, real talk. I've tried every serum on my feed, and this is the only one I've ever finished twice. Two drops, every morning. My skin just looks awake now.
Fish Audio S2 ProReady in 2 s · 0.02 credits
MiniMax Speech 2.8Ready in 7 s · 0.08 credits
Fish Audio Drama 3Ready in 3 s · 0.01 credits
Eleven v4Ready in 4 s · 0.07 credits
Eleven v4 TurboReady in 2 s · 0.04 credits

Voice models compared

ModelMade byModesLongest textInputsTest runTest costBest for
Fish Audio S2 ProFish AudioText to speech, multi-speaker dialogue—Script with bracketed directions2 s0.02 creditseven, natural reads and narration
MiniMax Speech 2.8MiniMaxText to speech—Script, voice description or a saved voice7 s0.08 creditsad voiceovers, UGC and narration
Fish Audio Drama 3Fish AudioText to speech, multi-speaker dialogue—Script with bracketed directions3 s0.01 creditsshort dramas, audiobooks and emotional ad reads
Eleven v4ElevenLabsText to speech10,000 characters (8,000 on AdAnt)Script with audio tags4 s0.07 creditsexpressive ad reads, characters and narration
Eleven v4 TurboElevenLabsText to speech—Script with audio tags2 s0.04 creditsdrafts, long scripts and fast turnaround

Test run and cost come from the same-script run above: the seconds until the finished file came back, and the credits for its characters. Longer scripts cost more; the try-it panel shows the price before you run.

Fish Audio S2 Pro key features

Directions in brackets

Like Drama 3, S2 Pro reads bracketed directions such as [shaky breath] without saying them aloud.

A calmer read

On the same directed line, S2 Pro stayed quiet and restrained where Drama 3 gave a trembling, tearful sigh. Pick it when you want subtle rather than theatrical.

The same voices as Drama 3

It uses Fish Audio's voice library, so one voice can read in both models. The example and the drama page use the same voice.

  1. Paste your script, with [directions] where the read should change.
  2. Press Create.
  3. Play it here, then hear Drama 3 on the same line on its page.

A script that works on S2 Pro

[how the line starts, e.g. quiet and tired] First sentence. [a sound, e.g. soft sigh] Second sentence.

Fish Audio S2 Pro: Expressive AI Text to Speech, Tried Online

Fish Audio S2 Pro is Fish Audio's expressive text-to-speech model from before Drama 3. It reads a script in a voice from Fish Audio's library and follows bracketed directions, with a more even delivery than Drama 3. AdAnt runs it with a fixed preset voice, so you can try it here without a Fish Audio account.

Narration

An even voice for explainers and long reads.

Ad voiceovers

A natural, unforced read for product videos.

Subtle scenes

Quiet hurt or calm warmth without the theatrics.

Fish Audio Drama 3

The same directed line on Drama 3, plus four directions to hear and the prompt syntax.

Fish Audio S2 Pro AI Voice Generator FAQ

Tips for a better result
  • Put the direction at the start of the line, in square brackets.
  • Ask for more than you want; S2 Pro plays emotions softer than Drama 3.
  • Use commas and short sentences where you want a pause.
Fish Audio S2 Pro vs Drama 3: which is better?

On our directed line Drama 3 acted more: a trembling sigh and a breaking voice, where S2 Pro stayed quiet and restrained. Drama 3 is also cheaper on OpenRouter ($0.01 against $0.015 per 1,000 characters, as of November 2026), so it is the default pick for drama; S2 Pro suits calmer reads.

Is Fish Audio S2 Pro free?

Running this model uses paid credits from an AdAnt plan. Creating an account is free. A short voice line costs well under 1 credit.

How much does S2 Pro cost?

$0.015 per 1,000 characters on OpenRouter (as of November 2026). On AdAnt our 10-second ad read used 0.02 credits.

Is there an S2 Pro API?

Yes: Fish Audio's own API, OpenRouter as fish-audio/s2-pro, or AdAnt's media API or the command adant-cli media audio generate --model fish-s2-pro, paid in AdAnt credits with no Fish Audio key.

Use Fish Audio S2 Pro for

Fish Audio S2 Pro compared by use case

Try another model

Compare every model

Want the whole ad, not just the voice?

AdAnt's agents research your market, write the script, pick the right model for each shot and make the video in one chat.

Start with AdAnt