Loquendo

Loquendo (loquendo.ai) is a Spanish-first speech synthesis site that treats the browser as a recording studio: write the script, pick a narrator voice, download the MP3. Its 655 voices can be filtered by accent, age, gender and language, and a PDF manuscript can be turned into an audiobook chapter by chapter. One point should be stated up front: the speech synthesis calls a third-party speech synthesis service (the site's privacy policy and voice preview assets point to ElevenLabs), and Loquendo neither develops nor trains voice models itself.

Core capabilities

• Text to speech: paste a script and pick a voice to get an MP3; the free allowance is 500 characters per request, and a subscription raises it to 10,000 characters
• A library of 655 voices: filter by accent, age, gender and language; the 37 Spanish voices go down to Latin American, Peninsular, Mexican, Colombian and Argentine
• Three quality tiers: Basic / Pro / Max map to different upstream models, Pro and Max require a subscription, and the Basic tier consumes 1 credit per 100 characters
• Voice cloning: upload or record 30–60 seconds of clean speech to create a private voice; uploading samples does not consume credits
• Audiobook workflow: import PDF / EPUB / TXT / DOCX (up to 20 MB), review chapter by chapter, assign a narrator per chapter, and export the whole book or separate tracks

Where it fits Spanish-language YouTube and TikTok creators making faceless narration, explainers and short-drama voiceover; independent authors and small publishers turning manuscripts into audiobooks; courses and corporate training that need both a Spanish and an English version; and anyone who wants to hear the result before paying can use the daily free allowance to try it out.

What sets it apart General-purpose TTS platforms are mostly English-centric; here everything from interface copy to voice filtering is built Spanish-first, and the accents go down to individual countries, which is the most tangible difference. Pricing sits close to upstream retail rates, and the product wins customers through localisation, an audiobook workflow and a no-login trial rather than through a technical moat.

Editorial verdict The pipeline is real: even anonymously you can complete input, synthesis and MP3 export and get actual audio back, which makes it worth treating as a day-to-day dubbing tool for Spanish content creators — run the free allowance dry first, then decide about paying. But script rewriting and polishing, speech transcription and subtitles, multi-speaker dialogue synthesis, and noise removal or speed and pitch tuning are all things it cannot do at all, so those needs belong with another tool; if you need a self-serve API and production-grade credentials, look elsewhere as well.