A free-to-try offline alternative to ElevenLabs for voiceovers
Natural-sounding text to speech on your own computer: podcast intros, YouTube narration, audiobook drafts — no credits, no character limits, $9 once.
Free · no account · 3 free uses of every tool · also for Mac (Intel), Windows, Linux
Cloud voice services such as ElevenLabs or Murf sound great, and they sell you characters per month. For narration where you don’t need a cloned voice, an open-source model now sounds natural enough for intros, explainers, e-learning and drafts.
What you get
- 10 voices — US and British English, male and female — from the Kokoro model (Apache-2.0), run offline through sherpa-onnx.
- Paste any amount of text; get a WAV file. Slower / normal / faster speed.
- No character limit, no account, no upload. Works on planes and on locked-down work laptops.
What it doesn’t do
No voice cloning, no emotion controls, and English voices only for now. If you need your own voice or a celebrity-grade performance, a paid cloud service is still better. For clear, natural narration at no per-character cost, this does the job.
Try it free
Download GUI Hub Audio (Text to Speech). Every tool works 3 times free; $9 once then unlocks every GUI Hub tool — no subscription, 30-day money-back guarantee. Prefer AI? Ask Claude or your agent: “Write a 30-second podcast intro and save it as intro.wav in a warm British voice.”
Try it now
Free download — use it 3 times free. $9 once unlocks everything. Prefer to ask your AI? GUI Hub also works as an MCP server for Claude, Cursor and others.