# Audio Transcription - Deepgram Nova-3, SRT, Diarization (`kaz_kakyo/audio-transcriber`) Actor

Transcribe audio and video URLs — speech-to-text with Deepgram Nova-3. Whisper alternative for meeting transcription, podcast transcripts, and SRT subtitles. Speaker diarization, summaries, language detection. Zero setup $0.010/min or BYOK $0.004/min.

- **URL**: https://apify.com/kaz\_kakyo/audio-transcriber.md
- **Developed by:** [Heim AI](https://apify.com/kaz_kakyo) (community)
- **Categories:** AI, Videos, Automation
- **Stats:** 72 total users, 61 monthly users, 94.1% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $10.00 / 1,000 audio minute (zero setup)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/platform/actors/running/actors-in-store#pay-per-event

## What's an Apify Actor?

Actors are web data automations that power AI and operations. They run on the Apify platform to scrape websites, process data, connect APIs, and automate workflows.
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.
Actors are written with capital "A".

## 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.
The best way to integrate Actors is as follows.

- **AI agents and MCP clients** — the [Apify MCP server](https://docs.apify.com/integrations/mcp.md) at `https://mcp.apify.com` (remote, streamable HTTP, OAuth on first use).
- **Agentic workflows and local Actor development** — [Agent Skills](https://apify.com/.well-known/agent-skills/index.json) with the [Apify CLI](https://docs.apify.com/cli/docs.md): `npm install -g apify-cli`, then `apify login`.
- **JavaScript/TypeScript projects** — the official [JS/TS client](https://docs.apify.com/api/client/js/docs.md): `npm install apify-client`.
- **Python projects** — the official [Python client](https://docs.apify.com/api/client/python/docs.md): `pip install apify-client`.
- **Any other language** — the [REST API](https://docs.apify.com/api/v2.md).

For usage examples, see the [API](#api) section below.

For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt).

# README

## Audio Transcriber — Deepgram Nova-3 Speech-to-Text

**URL in → transcript out.** Pass direct audio/video file URLs; get one JSON dataset row per file. Zero setup — no Deepgram key required. Built for **MCP agents, API clients, and scheduled pipelines** (that is how almost all usage runs today).

| | |
|---|---|
| **Actor id** | `kaz_kakyo/audio-transcriber` |
| **Minimal input** | `{ "audioUrls": ["https://…/file.mp3"] }` |
| **Cost** | **$0.010/min** zero-setup · **$0.004/min** BYOK · $0.00005/run start |
| **Output** | Dataset rows with `type: "transcript"` or `type: "error"` |

### Call it (MCP / API / schedule)

#### MCP (agents)

```json
{
  "actor": "kaz_kakyo/audio-transcriber",
  "input": {
    "audioUrls": ["https://example.com/interview.mp3"]
  }
}
```

Optional extras agents usually want:

```json
{
  "audioUrls": ["https://example.com/interview.mp3"],
  "diarize": true,
  "summarize": true,
  "includeSrt": true
}
```

After the run, read the default dataset. Every row has a `type` discriminator — filter on `"transcript"`; treat `"error"` as per-file failure. Bad/unsupported URLs become error rows and the run still **SUCCEEDS** (including all-failed batches) so agent mistakes do not look like platform outages. The run fails only on missing API key or Deepgram auth/credit errors.

#### API / `apify-client`

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

const client = new ApifyClient({ token: process.env.APIFY_TOKEN });
const run = await client.actor('kaz_kakyo/audio-transcriber').call(
  { audioUrls: ['https://example.com/interview.mp3'], diarize: true },
  { maxTotalChargeUsd: 1.0 }, // hard budget for this run
);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
const transcripts = items.filter((i) => i.type === 'transcript');
```

Same shape via REST: `POST /v2/acts/kaz_kakyo~audio-transcriber/runs` with your token, then poll or attach a webhook.

#### Make it recurring (what sticky callers do)

One-shot trials convert to spend when the same input path runs again without a human:

1. **Save a Task** in Console with your fixed options (`diarize`, `summarize`, language, BYOK key). Agents and cron jobs call the **task id**, not ad-hoc input.
2. **Schedule the Task** (hourly/daily) when URLs are stable — e.g. overnight meeting exports, or a podcast enclosure list you refresh elsewhere.
3. **Webhook on `SUCCEEDED`** to your endpoint / Zapier / Make — pull `defaultDatasetId` and process only `type === "transcript"` rows.
4. **Cap spend** on every automated run with `maxTotalChargeUsd` (platform run option). When the cap hits, remaining files become `type: "error"` skipped rows — no surprise bill, no silent free transcripts.
5. **Chain**: any scraper/RSS actor that outputs **direct media file URLs** → this actor. Page links (YouTube, Spotify, Drive *share* pages) fail preflight; download/resolve to a file URL first.

Long runs checkpoint finished URLs — a platform migration resumes without re-billing completed files.

### Output contract

One dataset item per input URL (plus skipped/invalid rows). Success shape:

```json
{
  "type": "transcript",
  "url": "https://example.com/interview.mp3",
  "transcript": "Full smart-formatted text…",
  "durationSeconds": 204.3,
  "minutesBilled": 4,
  "model": "nova-3",
  "language": "en",
  "confidence": 0.97,
  "summary": "…",
  "speakerTranscript": "Speaker 0: …\nSpeaker 1: …",
  "srt": "1\n00:00:00,000 --> …",
  "utterances": [{ "start": 0.0, "end": 3.2, "speaker": 0, "text": "…" }],
  "words": [{ "word": "Hello", "start": 0.0, "end": 0.4, "confidence": 0.99, "speaker": 0 }]
}
```

| Field | When present |
|---|---|
| `transcript`, `durationSeconds`, `minutesBilled`, `language`, `confidence`, `model` | always on success |
| `summary` | `summarize: true` (English audio) |
| `speakerTranscript` | `diarize: true` |
| `srt` | `includeSrt: true` |
| `utterances` / `words` | respective toggles |
| `wordsUrl` / `utterancesUrl` / `srtUrl` | rare — oversized payloads spilled to the key-value store |

Failure / skip row (never charged):

```json
{ "type": "error", "url": "https://…", "error": "…" }
```

Download the dataset as JSON, CSV, Excel, or HTML from Console or the dataset API.

### Why this one

- **Cheapest Deepgram on Apify.** Zero-setup $0.01/min ($0.60/h). BYOK $0.004/min actor fee + Deepgram wholesale ~$0.0043/min (~$0.50/h all-in). Typical Store incumbents: ~$0.015–$0.030/min.
- **Nova-3 by default** — or `nova-2` / `whisper-large`. Diarization, SRT, summaries, keyterm boosting.
- **HTTP-only.** Deepgram fetches your URL; the actor does not download media, so no proxy/compute surcharge.
- **Batch-safe for agents.** Bad links become `type: "error"` rows; URL/decode mistakes do not fail the run — only auth/credit problems do.

### Pricing

| Event | Price | When |
|---|---|---|
| Audio minute (zero-setup) | **$0.010** | No key — transcription included |
| Audio minute (BYOK) | **$0.004** | `deepgramApiKey` set — you pay Deepgram at cost |
| Actor start | $0.00005 | Per run |

Minutes round **up per file**. 90 s → 2 min → $0.02 zero-setup. 1 h meeting → $0.60 zero-setup, ~$0.50 all-in BYOK.

Deepgram new accounts get **$200 free credit** (no card) — ~775 h of Nova-3 pre-recorded before you pay Deepgram. BYOK pays for itself quickly on recurring volume.

### Input rules agents must follow

- **`audioUrls` (required)** — direct `https` links to files (`mp3`, `wav`, `m4a`, `flac`, `ogg`, `opus`, `mp4`, `mov`, `webm`, `mkv`, ≤2 GB). **Not** YouTube / TikTok / Spotify / SoundCloud / Vimeo / Apple Podcasts **page** URLs, and not Google Drive / Dropbox *share* pages (use a direct/`dl=1`/`raw=1` or signed file URL).
- **`deepgramApiKey`** — optional; encrypted; sent only to `api.deepgram.com`.
- **`model`** — `nova-3` (default), `nova-2`, `whisper-large`.
- **`language`** / **`detectLanguage`** — BCP-47 or auto-detect; `multi` + nova-3 for code-switching.
- **Toggles** — `diarize`, `smartFormat`, `paragraphs`, `summarize`, `includeSrt`, `includeUtterances`, `includeWords` (see Input tab).
- **`keyterms`** — nova-3 only; boost product names / jargon / speaker names.

Limits: 500 files/run, ~10 min Deepgram processing per file, concurrency 4 (2 for Whisper). Silent audio that decodes is still billed by duration.

See the **Input** tab for the full schema. See the **API** tab for run/dataset endpoints.

### FAQ

**Do I need a Deepgram account?** No. Bring a key only for the $0.004/min rate.

**What languages?** Nova-3: 30+. `whisper-large`: 90+ for rarer languages.

**Is my audio stored?** The actor never downloads or stores media — Deepgram fetches the URL; only transcript JSON lands in your dataset.

**Why did my URL fail?** It was not a direct, publicly reachable (or signed) media file. Resolve page URLs with a downloader first, then call this actor. The run still succeeds with `type: "error"` rows — check the dataset, not the run status.

**How do I keep costs predictable on a schedule?** Set `maxTotalChargeUsd` on the run/task. Prefer BYOK once volume is steady.

***

*If this saved you time, a Store review on the [actor page](https://apify.com/kaz_kakyo/audio-transcriber) helps a solo dev. Hit a problem? [Open an issue](https://apify.com/kaz_kakyo/audio-transcriber/issues).*

### Telemetry

Each run records one anonymous event: a salted hash of the caller account ID (never the raw ID), run origin (Console / API / MCP / …), and a timestamp. No inputs, results, or personal data — adoption measurement only.

# Actor input Schema

## `audioUrls` (type: `array`):

Required. Direct https links to media files (mp3, wav, m4a, flac, ogg, opus, mp4, mov, webm, mkv — up to 2 GB each). One dataset row per URL; max 500 per run. Minimal call: only this field. Do NOT pass YouTube/Spotify/SoundCloud/Vimeo/Apple Podcasts page URLs or Drive/Dropbox share pages — resolve to a direct or signed file URL first. Bad URLs become type:error rows; the run still succeeds.

## `deepgramApiKey` (type: `string`):

Optional. Leave empty for zero-setup at $0.010/min. Or bring your own free Deepgram key (console.deepgram.com — $200 credit, no card) and pay $0.004/min here plus Deepgram's wholesale ~$0.0043/min directly. Best for scheduled/API volume. Stored encrypted; sent only to api.deepgram.com.

## `model` (type: `string`):

Speech model. Default `nova-3` (fast, accurate, multilingual). `nova-2` = previous generation; `whisper-large` = rarer languages (runs at lower concurrency).

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

Optional BCP-47 code (e.g. `en`, `es`, `zh`, `de`). Leave empty for English, or set `detectLanguage`. Use `multi` with nova-3 for code-switched audio.

## `detectLanguage` (type: `boolean`):

Default: false. When true, detect the dominant language per file and transcribe in it. Overrides `language`.

## `diarize` (type: `boolean`):

Default: false. When true, adds `speakerTranscript` (`Speaker 0: …`) and speaker labels on SRT/utterances/words. Typical for meetings and interviews.

## `smartFormat` (type: `boolean`):

Default: true. Punctuation plus formatted dates, numbers, currency, phones, and emails in `transcript`.

## `paragraphs` (type: `boolean`):

Default: true. Split `transcript` into readable paragraphs instead of one wall of text.

## `summarize` (type: `boolean`):

Default: false. When true, adds `summary` (short abstract). English audio only — ignored for explicit non-English `language`.

## `includeSrt` (type: `boolean`):

Default: false. When true, adds `srt` (ready-to-save `.srt` string; speaker tags when `diarize` is on).

## `includeUtterances` (type: `boolean`):

Default: false. When true, adds `utterances[]`: `{ start, end, speaker, text }` per spoken segment. Useful for programmatic indexing.

## `includeWords` (type: `boolean`):

Default: false. When true, adds `words[]` with per-word timing and confidence. Large output on long audio — prefer utterances for most pipelines.

## `keyterms` (type: `array`):

Optional. Product names, jargon, or speaker names to boost recognition (nova-3 keyterm prompting). Ignored on other models.

## Actor input object example

```json
{
  "audioUrls": [
    "https://dpgr.am/spacewalk.wav"
  ],
  "model": "nova-3",
  "detectLanguage": false,
  "diarize": false,
  "smartFormat": true,
  "paragraphs": true,
  "summarize": false,
  "includeSrt": false,
  "includeUtterances": false,
  "includeWords": false
}
```

# Actor output Schema

## `overview` (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 = {
    "audioUrls": [
        "https://dpgr.am/spacewalk.wav"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("kaz_kakyo/audio-transcriber").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 = { "audioUrls": ["https://dpgr.am/spacewalk.wav"] }

# Run the Actor and wait for it to finish
run = client.actor("kaz_kakyo/audio-transcriber").call(run_input=run_input)

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

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

```

## CLI example

```bash
echo '{
  "audioUrls": [
    "https://dpgr.am/spacewalk.wav"
  ]
}' |
apify call kaz_kakyo/audio-transcriber --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "command": "npx",
            "args": [
                "mcp-remote",
                "https://mcp.apify.com/?tools=kaz_kakyo/audio-transcriber",
                "--header",
                "Authorization: Bearer <YOUR_API_TOKEN>"
            ]
        }
    }
}

```

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/acts/9WKjU5fxRBHDl4PKu/builds/dXWBOwfv4WSxdklA2/openapi.json