Text to Speech (Deepgram Aura)

Text to Speech converts any text into natural-sounding speech audio in seconds using Deepgram's Aura-2 AI voice models. Paste in a sentence or a paragraph, pick a voice and an audio format, and get back a ready-to-play audio file — MP3, WAV, FLAC, Opus, or AAC — that you can download, stream, or drop straight into your apps and automations.

No servers, no audio engineering, and no separate voice-API account to manage. Running on the Apify platform gives you API access, scheduling, monitoring, automatic retries, and one-click integration into automation tools like Make, Zapier, and n8n.

Why use Text to Speech?

• Accessibility — turn articles, docs, and notifications into audio people can listen to on the go.
• Voiceovers & narration — create natural voice tracks for videos, product demos, and e-learning courses.
• IVR & voice notifications — generate spoken prompts for phone systems, alerts, and voice assistants.
• Content at scale — batch-convert blog posts, newsletters, or scripts into audio automatically.
• Fast prototyping — hear how your copy sounds across many voices before you commit.

How to use Text to Speech

1. Click Try for free and open the Input tab.
2. Paste the text you want to convert (up to 2,000 characters per run).
3. Choose a voice (e.g. Aura 2 · Thalia) and an audio format (MP3 by default).
4. Click Start and wait a few seconds.
5. Open the Output tab to play and download your audio file.

That's it — no setup, no API keys, no coding required.

Input

Configure your run from the Input tab or via the API.

Field	Type	Description
text	string (required)	The text to convert to speech. Up to 2,000 characters.
model	string	Aura-2 voice model — featured voices across English, Spanish, Dutch, French, German, Italian, and Japanese. Default aura-2-thalia-en.
format	string	Output audio format: mp3, wav, flac, opus, or aac. Default mp3.
speed	string	Speaking-rate multiplier (1 = normal). Optional; not supported by all voices.

Example input:

{
    "text": "Welcome to our podcast. In today's episode, we explore how AI voices are changing the way we create and consume content.",
    "model": "aura-2-thalia-en",
    "format": "mp3"
}

Output

Your generated audio file is saved and made available for download, along with a data record describing the run. You can export the data in JSON, HTML, CSV, or Excel.

Example output record:

{
    "audioUrl": "https://api.apify.com/v2/key-value-stores/XXXX/records/audio-1784257804976.mp3",
    "audioKey": "audio-1784257804976.mp3",
    "text": "Welcome to our podcast. In today's episode...",
    "model": "aura-2-thalia-en",
    "format": "mp3",
    "characterCount": 118
}

Data table

Field	Description
audioUrl	Direct link to download the generated audio file.
audioKey	The name of the stored audio file.
text	The input text that was converted.
model	The voice used.
format	The audio format of the output file.
characterCount	Number of characters converted (used for billing).

Pricing

This Actor uses Apify's pay-per-event pricing — you pay a small, predictable amount per run with no separate voice-API bill to manage:

Charge	When it applies	What it covers
Run start	Once per run	Starting the run and spinning up the audio generation.
Characters converted	Per run	The text-to-speech generation itself, billed per character of text.

Because each run converts up to 2,000 characters, the cost per run is small and easy to predict. The exact prices are shown on this Actor's page in Apify Store, and all voice-generation costs are already included — you never need your own voice-API account.

New Apify users get free monthly usage credits to try the Actor at no cost.

Tips & advanced options

• Keep each run under 2,000 characters; split longer content into multiple runs.
• Choose wav or flac for lossless quality, or mp3/aac/opus for smaller files.
• Use the speed field to slow down or speed up narration where supported.
• Automate at scale by calling the Actor via the Apify API or by scheduling recurring runs.

FAQ and support

Which languages are supported? Aura-2 offers featured voices in English, Spanish, Dutch, French, German, Italian, and Japanese, with more added over time. Choose the model that matches your language.

Is there a character limit? Yes — up to 2,000 characters per run.

What audio formats can I get? MP3, WAV, FLAC, Opus, and AAC.

Can I use the audio commercially? Audio is generated with Deepgram's Aura-2 models; review Deepgram's terms for your specific use case.

Found a bug or have a feature request? Open an issue on this Actor's Issues tab. Custom voice or workflow needs can be accommodated on request.