Fish Audio
Drama 3
fish-audio/drama-3
Drama 3 is a text-to-speech model from Fish Audio built for directed voice performances. You write the direction in plain language in square brackets before a line, such as `[nervous,...
RoleTurns text into speech, or generates audio.
$2
In / M
Free
Out / M
—
Context
- AA intelligence index
- Not on listing
- Inputs
- text
- Outputs
- speech
- Tools
- Not listed
- Structured output
- Not listed
- Reasoning
- Not listed
- Weights
- Not verified
- Listed
- Oct 13, 2026
01 · What it's good at
Use it for this.
Three jobs this model is built for, and the ones to give to something else.
01
Voiceovers and spoken replies
Skip it for
- Transcribing a recording. That is a transcription model.
02 · Example tasks
What you'd actually send it.
Real inputs, not a benchmark. Paste one into the snippet below to try it.
You send
Read this 60-second product intro.
Why this model
Text in, audio out.
03 · Your stack
Where it sits: Draw, speak, listen.
Speech models output audio. Check the voices on the listing before you promise a brand voice.
Layer 01
Retrieve
Layer 02
Plan & reason
Layer 03
Do the volume
Layer 04
Gate & route
Layer 05 · this model
Draw, speak, listen
04 · Wire it up
One request. Paste and run.
Uses OpenRouter, so one key works for every model on this site. Set OPENROUTER_API_KEY and swap the prompt for one of the tasks above.
import { writeFile } from "node:fs/promises";
const res = await fetch("https://openrouter.ai/api/v1/audio/speech", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.OPENROUTER_API_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "fish-audio/drama-3",
"input": "Your report is ready.",
"voice": "<voice id from the listing>",
"response_format": "mp3"
}),
});
// The response body is the audio file itself.
await writeFile("reply.mp3", Buffer.from(await res.arrayBuffer()));
05 · Watch out for
Gotchas.
This lesson is generated from the model type and the live listing. It has not been hand-reviewed yet.
Check the listing for supported parameters before you rely on tools or structured output.
Sources
Lessons are written from each model's listing and the linked docs. We don't publish our own benchmark numbers; the index above is Artificial Analysis, as shown on OpenRouter.