A free ElevenLabs alternative for text to speech

Paste text, pick a voice, download the audio. No sign-up and no monthly credits to run out of: your own computer does the work.

Your text

Voice

Speed 1.0x

The first time, your browser fetches the voice (about 90 MB) and keeps it. After that it starts in seconds. English voices only.

Need it in your own app or workflow? The same job is an API: up to 2,000 characters as one MP3 per call, from two cents per 1,000 characters, no account and no monthly fee. OpenAI and ElevenLabs request formats work as they are. Text to speech API · Buy credits
Also in your tools: Make.com app · Obsidian plugin · Apify: audio and video transcriber · Apify: podcast transcriber

How it compares

Price: free here, with no character limit. ElevenLabs' API lists Flash at $0.04 and Multilingual v2 at $0.08 per 1,000 characters (its pricing page, read 14 November 2026), after an account.
Privacy: your text never leaves your computer.
For developers: our API takes ElevenLabs' own request format (POST /v1/text-to-speech/{voice_id}), from $0.02 per 1,000 characters, without an account. Full API comparison

Is it really free? Yes. Your own computer makes the speech, so there is no account, no character limit and no watermark.

Can I use the audio commercially? Yes. The voices come from the open Kokoro model (Apache-2.0); use the audio in videos, apps, courses and ads.

Is my text uploaded? No. The text stays on your computer. Only the voice model is downloaded, once.

Which languages? English, with American and British voices. For other languages, use the API's Spanish voices or another service.