National and local advertising
Radio, TV and social spots with the accent each campaign needs: Madrid, Andalusian, Canarian or standard.
121 voices from Spain with genuine accents: standard Peninsular, northern, Andalusian, Canarian, Madrid… plus Latin American Spanish on its own page. Direct them line by line and download at 48 kHz.
Hear the demos before you sign up. Every voice comes with casting notes and documented provenance.
121 voices

Mid-range · Clean · Friendly
Ideal for radio spots and online ads.

Deep · Resonant · Warm
Ideal for documentaries and video narration.

Deep · Youthful · Friendly
Ideal for radio spots and online ads.

High-pitched · Youthful · Clean
Ideal for corporate video and online ads.

Mid-range · Clean · Measured
Ideal for video narration and online ads.

Mid-range · Clean · Energetic
Ideal for online ads and radio spots.

Deep · Clean · Friendly
Ideal for video narration and online ads.

Deep · Warm · Authoritative
Ideal for documentaries and video narration.

Mid-range · Warm · Neutral
Ideal for e-learning and corporate video.

Deep · Warm · Authoritative
Ideal for documentaries and audiobooks.

Neutral · Deep · Velvety
Ideal for e-learning and corporate video.

Mid-range · Clean · Friendly
Ideal for video narration and online ads.
Pick a line or write your own, hear the voices and generate the audio in the studio.
Your text is copied to the clipboard: paste it in the studio.
Write the intention in brackets and the voice performs it. Castilian Spanish gets the full set: 32 emotions, 18 voice effects and 9 styles. Tags are free.
[upbeat]¡Buenos días, Madrid! [hushed]Pero antes, os cuento un secreto… [belly laugh]¡Nadie se había dado cuenta!
Native voices sound local. The rest read Castilian Spanish clearly, with a hint of their own language: just right for a character from abroad, a brand that wants one voice in every market, or your own cloned voice.
Theodore is American. You can hear it in his Spanish, and sometimes that is exactly the point.
Radio, TV and social spots with the accent each campaign needs: Madrid, Andalusian, Canarian or standard.
Corporate and academy courses with the same voice in every module.
Fiction, non-fiction and documentaries with deep, measured voices built for hours of listening.
Switchboards, hold messages and announcements, as telephony WAV at 8 or 16 kHz.
One endpoint for all 55+ languages. Pass "language": "es" and pick any voice.
import os, requests res = requests.post( "https://api.voicefinder.io/v1/text-to-speech/f7b60877-0f7b-4301-a50b-50eaad0a3ec4", # Casandra headers={"x-api-key": os.environ["VOICEFINDER_API_KEY"]}, json={"text": "Este sábado abrimos a las diez. Te esperamos con churros y chocolate para los cien primeros.", "language": "es", "output_format": "mp3"},)res.raise_for_status()open("speech.mp3", "wb").write(res.content)Each with its own voices, demos and page.
One with voices that do not sound translated. Voicefinder gives you 121 voices in Castilian Spanish on Voyager 1, our own model: broadcast quality at 48 kHz, direction with emotions and voice effects, and every file marked with an inaudible watermark and Content Credentials (C2PA). You can hear them on this page before you sign up.
Yes. 100 voices have Castilian Spanish as their main language, with the accent of people who really speak it, and 21 more speak it as a second language. Each one has documented provenance.
Yes. All 800+ Voicefinder voices speak all 55+ languages. Native voices sound local; the rest read Castilian Spanish clearly with a hint of their own language, which works well for a character from abroad or for keeping one brand voice across every market. Your own cloned voice can speak Castilian Spanish too.
Yes, with the full set of tags. Write the intention in brackets, such as [upbeat], [hushed] or [belly laugh], and the voice performs it: 32 emotions, 18 voice effects like laughs and sighs, and 9 reading styles. Tags are free.
The same as any other language: one credit per character. The Free plan gives you 10,000 credits a month for personal use; commercial use starts with Basic at $12 a month, and yearly billing makes every plan 30% cheaper.
Call POST /v1/text-to-speech/{voice_id} with "language": "es", which sets the language (without it, the model infers it from the text and the voice). The API is on every plan and the audio comes back at 48 kHz, marked.
Free plan for personal use. Commercial use from $12 a month.