Fish Audio · Transcription
Fish Transcribe 1 Pro API price
Fish Audio’s Fish Transcribe 1 Pro through one prepaid, OpenAI-compatible key: $0.006 per minute, the provider’s list price with nothing added per request.
Fish Transcribe 1 Pro price
- Price
- $0.006per minute
- $0.36 per audio hour
Fish Audio’s list price, in US dollars. Tokens.Pay adds a 5% fee (minimum $0.79) when you add credit, never per request.
What Fish Transcribe 1 Pro is good at
Speaker turns and emotion cues written into the transcript.
In short: speaker turns and cues in the transcript.
Transcription model, called at /v1/audio/transcriptions. Listed under speech to text.
Fish Transcribe 1 Pro endpoint and id
- Provider
- Fish Audio
- Type
- Transcription
- Endpoint
/v1/audio/transcriptions- Model id
fish-transcribe-1-pro
What Fish Transcribe 1 Pro costs per request
The list price, multiplied out.
| Minutes of audio | Cost |
|---|---|
| 1 | $0.006000 |
| 60 | $0.3600 |
| 600 | $3.60 |
At $0.006 per minute ($0.36 per audio hour), Fish Audio’s list price.
Fish Transcribe 1 Pro cost calculator
Set how much you need. The provider bills per unit; this is the arithmetic.
Call Fish Transcribe 1 Pro with the OpenAI SDK
Base URL https://api.airuntime.dev/v1, your key as the bearer token, and model set to fish-transcribe-1-pro.
curl
curl https://api.airuntime.dev/v1/audio/transcriptions \
-H "Authorization: Bearer $TOKENS_PAY_KEY" \
-F model="fish-transcribe-1-pro" \
-F file="@meeting.mp3"Python
from openai import OpenAI
import os
client = OpenAI(base_url="https://api.airuntime.dev/v1", api_key=os.environ["TOKENS_PAY_KEY"])
with open("meeting.mp3", "rb") as audio:
text = client.audio.transcriptions.create(model="fish-transcribe-1-pro", file=audio)
print(text.text)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 text = await client.audio.transcriptions.create({ model: "fish-transcribe-1-pro", file: fs.createReadStream("meeting.mp3") });
console.log(text.text);Who processes Fish Transcribe 1 Pro requests
Your code calls AI Runtime directly. It forwards the request to the provider and keeps only the bill.
Processing and storage
- 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
Compare Fish Transcribe 1 Pro with similar models
| Model | Provider | Price |
|---|---|---|
| Fish Transcribe 1 Pro (this page) | Fish Audio | $0.006 per minute |
| Transcription Fast | OpenAI | $1.25 per 1M audio tokens |
| Transcription Accurate | OpenAI | $2.50 per 1M audio tokens |
Fish Transcribe 1 Pro API questions
How much does the Fish Transcribe 1 Pro API cost?
$0.006 per minute, Fish Audio’s list price. Tokens.Pay adds nothing per request; a 5% fee (minimum $0.79) applies when you add credit.
What is the model id for Fish Transcribe 1 Pro?
Send model "fish-transcribe-1-pro" to https://api.airuntime.dev/v1/audio/transcriptions with your Tokens.Pay key as the bearer token. Any OpenAI-compatible SDK works.
Does Tokens.Pay store my Fish Transcribe 1 Pro prompts?
No. AI Runtime, the gateway your key calls, keeps prompts and outputs in memory only while the request runs and stores just the billing record. The request is processed by Fish Audio, under the provider’s own API data terms.
Add credit, then call Fish Transcribe 1 Pro.
From $5, plus a 5% top-up fee (minimum $0.79). No subscription; paid credit never expires.
Add credit