Fish Audio
Fish Audio API pricing
Expressive speech in 83 languages, and transcripts that mark speaker turns. Every Fish Audio model on Tokens.Pay at its list price, through one prepaid, OpenAI-compatible key.
3 models · processed by Fish Audio
Fish Audio API prices
| Model | Endpoint | Price |
|---|---|---|
| Fish S2.1 Pro | /v1/audio/speech |
$0.015 per 1K bytes |
| Fish S2.1 Pro Free | /v1/audio/speech |
Free per 1K bytes |
| Fish Transcribe 1 Pro | /v1/audio/transcriptions |
$0.006 per minute |
Fish Audio’s list prices in US dollars. Tokens.Pay adds a 5% fee (minimum $0.79) when you add credit, never per request.
Where Fish Audio requests go
Your code calls AI Runtime, which forwards the request to the provider and keeps only the bill.
Who processes your requests
- Model provider
- Fish Audio · data terms
- Gateway
- AI Runtime, AWS us-east-1
Not stored by Tokens.Pay or AI Runtime. Prompts and outputs exist in memory only while the request runs; we keep the billing record. The provider processes the request under its own terms. Zero data retention, exactly
Call Fish S2.1 Pro with the OpenAI SDK
Base URL https://api.airuntime.dev/v1, your key as the bearer token. Swap the model id for any Fish Audio model above.
curl
curl https://api.airuntime.dev/v1/audio/speech \
-H "Authorization: Bearer $TOKENS_PAY_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "fish-s2-1-pro", "input": "Your credit has arrived."}' \
--output speech.mp3Python
from openai import OpenAI
import os
client = OpenAI(base_url="https://api.airuntime.dev/v1", api_key=os.environ["TOKENS_PAY_KEY"])
audio = client.audio.speech.create(model="fish-s2-1-pro", input="Your credit has arrived.")
audio.write_to_file("speech.mp3")Node
import fs from "node:fs";
import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.airuntime.dev/v1", apiKey: process.env.TOKENS_PAY_KEY });
const audio = await client.audio.speech.create({ model: "fish-s2-1-pro", input: "Your credit has arrived." });
fs.writeFileSync("speech.mp3", Buffer.from(await audio.arrayBuffer()));Fish Audio API questions
How much does the Fish Audio API cost?
Fish S2.1 Pro: $0.015 per 1K bytes; Fish S2.1 Pro Free: free; Fish Transcribe 1 Pro: $0.006 per minute. These are Fish Audio’s list prices; Tokens.Pay adds nothing per request, and a 5% fee (minimum $0.79) applies when you add credit.
Can I call Fish Audio models with the OpenAI SDK?
Yes. Point the OpenAI SDK at https://api.airuntime.dev/v1, use your Tokens.Pay key as the API key, and set model to an id such as "fish-s2-1-pro". The same key calls every model on Tokens.Pay.
Where are Fish Audio requests processed?
By Fish Audio, under its own API data terms, through AI Runtime on AWS us-east-1. Tokens.Pay and AI Runtime do not store prompts or outputs.
More models
Add credit, then call Fish Audio.
From $5, plus a 5% top-up fee (minimum $0.79). No subscription; paid credit never expires.
Add credit