Bulk Text to Speech — MP3 + SRT Subtitles (No API Key)

Convert text to speech in bulk — no API key, no subscription, no character limits from expensive TTS providers. This Actor turns every text you give it into a natural-sounding MP3 voiceover using 322 neural AI voices in 75+ languages, and generates perfectly timed SRT/VTT subtitles next to every file. Run it from the Apify Console, on a schedule, through the API, or call it from an AI agent via Apify MCP.

What does Bulk Text to Speech do?

• 🎙️ Text to MP3 at scale — paste 1 or 500 texts; each becomes its own MP3 voiceover, generated in parallel
• 📝 Subtitles included — every clip ships with a matching SRT or VTT file, timed from the actual speech engine (not guessed), in sentence blocks or word-by-word TikTok-style captions
• 🌍 322 neural voices, 75+ languages — US/UK/AU English, Spanish, French, German, Arabic, Hindi, Japanese, Chinese, Portuguese and more, including multilingual voices that switch language automatically
• ⚡ Speed & pitch control — from half speed to 2×, deeper or higher pitch
• 🔗 Merge option — combine all clips into one continuous combined.mp3 with one continuous subtitle track (podcasts, audiobooks, full videos)
• 🔑 No API key needed — unlike ElevenLabs, OpenAI TTS or Google Cloud, there is nothing to sign up for and no key to paste

Why use this text to speech API?

Use case	How this Actor helps
Faceless YouTube / TikTok channels	Batch-generate voiceovers + word-by-word captions for every script in one run
Shorts & Reels automation	Chain with video tools via API, Make, Zapier or n8n — text in, MP3 + SRT out
E-learning & courses	Narrate lessons in 75+ languages with consistent voices
Podcasts & audiobooks	Merge chapters into a single MP3 with continuous subtitles
IVR & product demos	Professional prompts without studio costs
Accessibility	Give every article or newsletter an audio version automatically

Compared to ElevenLabs (~$0.15–0.30 per 1,000 characters) or hiring voice talent, this Actor costs a fraction of a cent per clip — and it scales to thousands of clips per run on Apify's infrastructure with scheduling, webhooks and 6,000+ integrations.

How to convert text to speech in bulk

1. Open the Actor and paste your texts into Texts to convert — one entry per clip.
2. Pick a Voice from the dropdown (or run once with List all voices to browse all 322).
3. Optionally set speed, pitch, and the subtitle style (sentence blocks or word-by-word).
4. Click Start. Each clip appears in the Output tab with an MP3 download link and a subtitles download link.
5. Download files individually, grab them via API, or export the whole table as JSON/CSV/Excel.

That's it — no account with a TTS provider, no API key, no setup.

Input example

{
    "texts": [
        "Did you know the average person spends six years dreaming?",
        "Follow for more daily facts that will blow your mind."
    ],
    "voice": "en-US-ChristopherNeural",
    "speed": "+25%",
    "generateSubtitles": true,
    "subtitleGranularity": "word",
    "subtitleFormat": "srt"
}

Output example

Each clip becomes one dataset item with direct download links:

{
    "index": 1,
    "kind": "audio",
    "text": "Did you know the average person spends six years dreaming?",
    "characters": 59,
    "voice": "en-US-ChristopherNeural",
    "audioUrl": "https://api.apify.com/v2/key-value-stores/.../records/audio-001.mp3",
    "subtitlesUrl": "https://api.apify.com/v2/key-value-stores/.../records/subtitles-001.srt",
    "durationSeconds": 4.32,
    "speed": "+25%",
    "pitch": "+0Hz",
    "status": "ok"
}

Download results as JSON, CSV, Excel or XML, or fetch the MP3/SRT files directly from the key-value store URLs.

Data fields

Field	Description
index	Position of the text in your input list
text	The converted text
characters	Characters synthesized (what you're billed on)
voice	Neural voice code used
audioUrl	Direct MP3 download link
subtitlesUrl	Direct SRT/VTT download link
durationSeconds	Audio length in seconds
speed / pitch	Voice settings used
status	ok when the clip generated successfully

How much does bulk text to speech cost?

You pay a tiny amount per 1,000 characters converted — see the Pricing tab for exact rates. There are no subscriptions and no minimums: 10 TikTok scripts of ~300 characters each cost less than a cent. Free-plan users can convert up to 10 texts / 3,000 characters per run; subscribe to any Apify plan to unlock unlimited texts and characters.

Tips for the best AI voiceovers

• TikTok/Shorts pacing: use +25% speed with subtitleGranularity: "word" for snappy animated captions.
• Voice discovery: run once with List all voices ON — the dataset then contains all 322 voices with language, gender and personality tags. Put your favorite's code into Custom voice code.
• Multilingual scripts: pick a Multilingual voice (Ava, Emma, Andrew, Brian) and it will switch languages mid-text automatically.
• Long content: enable merge to get one continuous MP3 + subtitle track in input order.
• Automation: trigger this Actor from Make, Zapier, n8n, or an AI agent via Apify MCP — the input is a simple JSON array of strings.

FAQ — Text to Speech on Apify

Is this a free text to speech API?

You can try it free (10 texts / 3,000 characters per run on the Apify free plan). Beyond that you pay per 1,000 characters — no monthly subscription, no API-key signup.

Do I need an ElevenLabs or OpenAI API key?

No. This Actor needs no API key at all. It uses Microsoft Edge's neural text-to-speech voices, which are free to use — you only pay the small Apify per-character fee.

Which languages and voices are supported?

322 neural voices across 75+ languages and dialects, including English (US, UK, AU, IN), Spanish, French, German, Italian, Portuguese, Arabic, Hindi, Japanese, Korean, Chinese, Russian, Turkish, Dutch, Polish, Vietnamese and Thai. Run the Actor with List all voices to export the full catalog.

Can it generate TikTok-style word-by-word captions?

Yes — set Subtitle timing to word-by-word and every word gets its own timed cue in the SRT/VTT file, ready for CapCut, Premiere or DaVinci Resolve caption animations.

How accurate are the subtitle timestamps?

The timestamps come from the speech engine's own word/sentence boundary events during synthesis, so they match the audio exactly — no re-alignment or guessing.

Can I call it from my own app or an AI agent?

Yes. Every Apify Actor is also an HTTP API: POST your input JSON and read the dataset when the run finishes. AI agents can call it directly through the Apify MCP server.

Is there a limit on text length?

Long texts are handled automatically — a 10,000-word article becomes one MP3. Free-plan runs are capped at 3,000 characters total; paid plans have no cap.

Support & custom solutions

Found an issue or want a feature? Open a ticket in the Issues tab — it's monitored daily.

💼 Need a custom automation or a private version of this Actor (different voices, S3 upload, video rendering)? Reach out at youssefarhan24@gmail.com.

🌐 Got another tool or site in mind? Suggest it here.

This Actor uses publicly available text-to-speech technology. You are responsible for how you use the generated audio and for complying with the laws applicable to your content.