# Whisper Turbo Speech to Text — AI Transcription (`myagizm/whisper-turbo-speech-to-text`) Actor

Transcribe WAV audio with Whisper large-v3-turbo. Timestamped segments, auto language detection. $0.01 per started audio minute — one all-inclusive price.

- **URL**: https://apify.com/myagizm/whisper-turbo-speech-to-text.md
- **Developed by:** [MYM](https://apify.com/myagizm) (community)
- **Categories:** AI, Videos, Automation
- **Stats:** 1 total users, 0 monthly users, 0.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

$10.00 / 1,000 started audio minute (all-inclusive)s

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## Whisper Turbo Speech to Text — Fast AI Transcription API ($0.60 per audio hour)

**Transcribe speech to text with Whisper large-v3-turbo — one flat all-inclusive price, no subscriptions, no hidden platform fees.**

Built for AI agents, LLM pipelines, n8n / Zapier / Make automations, media teams and researchers. Pay only for successful, non-empty transcripts.

![Type](https://img.shields.io/badge/type-Paid%20API-blue) ![Model](https://img.shields.io/badge/model-Whisper%20large--v3--turbo-green) ![Price](https://img.shields.io/badge/price-%240.01%20%2F%20audio%20minute-brightgreen) ![Input](https://img.shields.io/badge/input-WAV%20up%20to%2010%20min-orange)

### Table of contents

- [What can it do](#what-can-it-do)
- [Who uses it](#who-uses-it)
- [Input fields](#input-fields)
- [How to use](#how-to-use)
- [Output example](#output-example)
- [Pricing](#pricing)
- [Integrations and API](#integrations-and-api)
- [Tips](#tips)
- [FAQ](#faq)
- Related searches
- [Disclaimer](#disclaimer)
- [中文说明](#中文说明)

### What can it do

✅ Transcribe an audio file (PCM WAV, up to 25 MiB / 10 minutes) into text
✅ Whisper large-v3-turbo model — fast and accurate
✅ 15 selectable languages + fully automatic language detection
✅ Word/sentence-level segments with timestamps
✅ One flat all-inclusive price per started audio minute — no start fee, no platform surcharge
✅ Charges only for a successful, non-empty transcript — failed runs cost nothing
✅ Works with AI agents and LLM tools via standardized input/output

### Who uses it

- **AI agent developers** feeding meeting or voice-note transcripts into LLMs
- **Automation builders** on n8n, Zapier, Make archiving podcasts and calls
- **Journalists and researchers** transcribing interviews
- **Content teams** generating subtitles and drafts
- **Accessibility teams** captioning audio

### Input fields

| Field | Type | Required | Description |
| --- | --- | --- | --- |
| `audioUrl` | string | ✅ | Direct public HTTPS URL to an uncompressed PCM WAV file. No redirects, no credentials. Maximum 25 MiB and 600 seconds. Billing counts started minutes of the decoded clip ($0.01 per started minute, minimum one block). |
| `language` | select | ❌ | `auto` (default) detects automatically, or force one of: en, tr, de, fr, es, it, pt, ja, ko, ar, ru, uk, nl, pl. |

### How to use

1. **Host your WAV** anywhere public (cloud storage, your server, or our free [soundupload.tr.foxtools.de](https://soundupload.tr.foxtools.de) upload page) and copy the direct HTTPS link.
2. **Paste the link** into `audioUrl`.
3. **Set the language** or leave `auto`.
4. **Run** — the transcript, segments and billing details appear in the Output tab and dataset.

#### Input example

```json
{
  "audioUrl": "https://example.com/interview.wav",
  "language": "en"
}
```

### Output example

Real run output (abridged):

```json
{
  "ok": true,
  "kind": "stt",
  "language": "en",
  "text": "Thanks for joining. Today we are talking about speech to text.",
  "duration": 63.8,
  "segments": [
    { "start": 0.0, "end": 2.4, "text": "Thanks for joining." }
  ],
  "billingUnit": "audio-minute",
  "billingQuantity": 63.8,
  "billingQuantityUnit": "audio-seconds",
  "billingCount": 2,
  "billingPriceUsdPerBlock": 0.01,
  "totalChargeUsd": 0.02,
  "billingIsAllInclusive": true
}
```

### Pricing

**$0.01 per started audio minute — all-inclusive.**

The math, shown plainly:

| Audio length | Blocks (`ceil(seconds/60)`) | Cost |
| --- | --- | --- |
| 1–60 s | 1 | $0.01 |
| 61–120 s | 2 | $0.02 |
| 10 min (max) | 10 | $0.10 |
| 60 min (6 runs) | 60 | **$0.60** |

That equals **$0.60 per audio hour** — far below most major cloud transcription APIs. One price covers inference, Apify platform usage and delivery. No separate start fee. Minutes are charged only for a successful, non-empty transcript; failed or empty runs cost $0.

### Integrations and API

**Sync run (get dataset items directly):**

```bash
curl -X POST "https://api.apify.com/v2/acts/myagizm~whisper-turbo-speech-to-text/run-sync-get-dataset-items?token=YOUR_APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"audioUrl":"https://example.com/interview.wav","language":"en"}'
```

**Async run:**

```bash
curl -X POST "https://api.apify.com/v2/acts/myagizm~whisper-turbo-speech-to-text/runs?token=YOUR_APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"audioUrl":"https://example.com/meeting.wav"}'
```

**n8n / Zapier / Make:** use the Apify node, pick this actor, map your URL field to `audioUrl`.

### Tips

💡 Use 16 kHz mono PCM WAV for the best speed/accuracy balance.
💡 `auto` language detection is strong — set a language only for short or noisy clips.
💡 For clips longer than 10 minutes, split them and run per chunk.
💡 Segments include timestamps — ideal for subtitles.

### FAQ

**Q: Which formats are accepted?** Uncompressed PCM WAV only (max 25 MiB, 600 s). Redirects, credentials and compressed containers are rejected.

**Q: Where can I host my audio?** Any public HTTPS direct link. Easiest way: our free upload page at **[soundupload.tr.foxtools.de](https://soundupload.tr.foxtools.de)** — upload your WAV (up to 5 minutes per clip), copy the direct link it gives you, and paste it into `audioUrl`. No account needed.

**Q: What are the upload limits on soundupload?** Per clip: 5 minutes / 25 MiB. Per IP: up to 5 hours of audio in any 10-minute window, up to 24 hours per day. When you reach 80% of a quota the page shows a warning. Need more? Email **info@metanetsoft.com** to have your IP whitelisted (limits removed for whitelisted IPs).

**Q: Do failed runs cost money?** No. Charges apply only to a successful, non-empty transcript.

**Q: How accurate is it?** Whisper large-v3-turbo is one of the strongest open transcription models; accuracy depends on audio quality.

**Q: Which languages?** Auto-detect plus 15 forced options: en, tr, de, fr, es, it, pt, ja, ko, ar, ru, uk, nl, pl.

**Q: Do I get timestamps?** Yes — every run returns timestamped segments.

**Q: Is my audio stored?** The actor fetches your URL, transcribes and returns text. The download URL you provide is your own storage.

**Q: Can I transcribe phone calls?** Yes, if you can export them as PCM WAV within the size and duration limits.

### Related searches

whisper api · speech to text api · transcription api · whisper turbo · cheap transcription api · audio to text · podcast transcription · interview transcription · turkish speech to text · german transcription api · stt for n8n · stt for zapier · ai transcription · openai whisper alternative

### Disclaimer

Transcription quality depends on your source audio. We do not claim accuracy equivalence with any third-party service.

### 中文说明

## Whisper Turbo 语音转文字 — $0.60 / 小时音频

**使用 Whisper large-v3-turbo 转录语音 — 一个全包价，无订阅、无隐藏费用。**

✅ PCM WAV 输入，最大 25 MiB / 10 分钟
✅ 自动语言检测 + 15 种可指定语言
✅ 带时间戳的分段结果
✅ 计费：每开始的一分钟 $0.01，失败不收费

#### 输入字段

| 字段 | 类型 | 必填 | 说明 |
| --- | --- | --- | --- |
| `audioUrl` | string | ✅ | 公开 HTTPS 直链 PCM WAV |
| `language` | select | ❌ | auto 或指定语言 |

#### 计费示例

| 音频长度 | 块数 | 费用 |
| --- | --- | --- |
| 1–60 秒 | 1 | $0.01 |
| 61–120 秒 | 2 | $0.02 |
| 60 分钟 | 60 | $0.60 |

#### 相关搜索

语音转文字 API · Whisper API · 便宜转录 API · 播客转录 · 土耳其语转写 · n8n 语音转文字

# Actor input Schema

## `audioUrl` (type: `string`):

Public HTTPS, no redirects. PCM WAV only, maximum 25 MiB and 10 minutes. Billing counts started audio minutes of the decoded clip ($0.01 per started minute, minimum one block).

## `language` (type: `string`):

Auto detects language; select a known language to force it.

## Actor input object example

```json
{
  "language": "auto"
}
```

# Actor output Schema

## `result` (type: `string`):

No description

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {};

// Run the Actor and wait for it to finish
const run = await client.actor("myagizm/whisper-turbo-speech-to-text").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {}

# Run the Actor and wait for it to finish
run = client.actor("myagizm/whisper-turbo-speech-to-text").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{}' |
apify call myagizm/whisper-turbo-speech-to-text --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,myagizm/whisper-turbo-speech-to-text"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/7dzkjArBsThI9GdIP/builds/Uo60aZuPVsXk0GXOa/openapi.json