Multilingual Text to Speech (54 Voices) — by Brainiall

Convert text into natural, high-fidelity human speech across 54 realistic voices and multiple languages — optimized for podcasts, audiobooks, AI assistants, video voiceovers and localization pipelines.

Give it one or more text blocks and get back crisp audio files stored in the run Key-Value store, formatted in MP3, WAV or Opus, with public URLs pushed directly to your Apify dataset.

What it does

• Multilingual speech synthesis — Generate natural-sounding speech across 54 distinct voices covering English, Spanish, Portuguese, French, German, Italian and more.
• Multiple audio containers — Choose between mp3 (universal playback), wav (lossless quality for editing), or opus (ultra-compact storage/streaming).
• Batch processing — Pass a list of text paragraphs, chapters or script lines to process multiple audio tracks concurrently.
• Key-Value audio storage — Binary audio files are stored in your run's Key-Value store, returning lightweight HTTP URLs in the dataset output.
• Custom speed & tone control — Adjust speech velocity rate from 0.5x (slow) to 2.0x (fast).

Powered by the Brainiall Text-to-Speech engine (api.brainiall.com) — high-performance speech synthesis engineered for enterprise applications.

Who it's for

• Content creators & Podcasters — Automate voiceovers for YouTube shorts, podcasts, and social media posts.
• E-learning & Publishers — Convert articles, documentation, blog posts, and educational modules into engaging audiobooks.
• AI Agent & App Developers — Provide text-to-speech output for conversational AI agents, interactive voice response (IVR) systems, and accessibility tools.
• Localization Teams — Translate and synthesize audio in multiple global languages with matching voice accents.

Input

{
    "texts": [
        "Welcome to Brainiall Text to Speech service.",
        "Transform any written content into natural sounding voice audio across 54 realistic voices."
    ],
    "voice": "brainiall-en-us-1",
    "speed": 1.0,
    "lang": "en",
    "format": "mp3"
}

Field	Type	Description	Default
texts	Array	List of text strings to synthesize into speech audio files.	Required
voice	String	Voice ID identifier (e.g. brainiall-en-us-1, brainiall-pt-br-1). 54 voices available.	brainiall-en-us-1
speed	Number	Speech speed multiplier rate (0.5 = slow, 1.0 = normal, 2.0 = fast).	1.0
lang	String	Language code (e.g. en, pt, es, fr, de). Auto-detected if omitted.	en
format	String	Output audio format: "mp3", "wav", or "opus".	"mp3"

Output

One dataset item per input text block:

{
    "index": 0,
    "text": "Welcome to Brainiall Text to Speech service.",
    "character_count": 44,
    "voice": "brainiall-en-us-1",
    "lang": "en",
    "speed": 1.0,
    "format": "mp3",
    "audio_key": "audio_1.mp3",
    "audio_url": "https://api.apify.com/v2/key-value-stores/xyz123/records/audio_1.mp3",
    "audio_size_bytes": 68420,
    "status": "success"
}

Export results as JSON, CSV, Excel, or download the raw audio files directly via the provided audio_url endpoints.

Pricing

You pay per synthesized character (character-synthesized event). Failed requests or empty items are never charged. Costs scale transparently with the exact volume of text you convert.

Tips

• For video editing software (Premiere, Final Cut, DaVinci), use format: "wav" for uncompressed audio quality.
• For web/mobile app playback or low-bandwidth storage, use format: "mp3" or format: "opus".
• Split long books or scripts into paragraph-level array items (texts) to process sections concurrently and get faster overall completion times.

---

Built and maintained by Brainiall — production AI APIs for speech, documents, vision and the web.