Independent research for creator workflowsOfficial sources & verified limits. How we review

Voice tool profile

Kokoro TTS

An open-source text-to-speech model from Hexgrad with 82M parameters (Apache 2.0). Studio-quality speech at nearly 100x real-time; ~48 voices across 8 languages in community builds; runs locally or via hosted demos.

Official sourcesIndependent researchPricing notesHow we review
Best for
Developers and creators who want free, self-hosted TTS without per-character fees, and who can handle model setup.
Starting point
Free and open source (Apache 2.0 license).
Free plan
Yes — Entire model is free (Apache 2.0).
Key limitation
Requires local setup/technical skill — not a plug-and-play SaaS.

Choose it if

Developers and creators who want free, self-hosted TTS without per-character fees, and who can handle model setup.

Avoid it if

  • Requires local setup/technical skill — not a plug-and-play SaaS.
  • Voice quality below top commercial engines (ElevenLabs) for emotional range.
  • Community voice packs vary; official model focuses on a smaller voice set.

Free-plan suitability

Entire model is free (Apache 2.0). No account or credits needed for self-hosted use; hosted demo sites offer free generation.

Where it fits

Developers and creators who want free, self-hosted TTS without per-character fees, and who can handle model setup.

Developerscreatorshobbyiststext-to-speechvoiceoverself-hosted tts

Browse all Voice tools in the catalog

Pricing note

Starting point
Free and open source (Apache 2.0 license).
Free plan
Yes — Entire model is free (Apache 2.0).

Free and open source (Apache 2.0 license). Self-hosted — no subscription; run locally or on your own hardware. 82M-parameter model, ~100x real-time generation speed. Hosted demos (TTS.ai, Rewind.ai, Unreal Speech) are free to try; commercial services built on Kokoro may charge.

Verify the current plan, credits, output limits, and commercial terms before purchasing.

Estimate your voice cost

Is it legit?

Who is behind Kokoro TTS, where it is based, and what is publicly known about its funding. Company details change — verify on the official site before committing.

Company
Hexgrad (community project)
Founded
2024
Funding
Open-source (Apache 2.0); HF Space by hexgrad; used by TTS.ai, Rewind.ai, Unreal Speech

Free plan details

Entire model is free (Apache 2.0). No account or credits needed for self-hosted use; hosted demo sites offer free generation.

Trade-offs to check

  • Requires local setup/technical skill — not a plug-and-play SaaS.
  • Voice quality below top commercial engines (ElevenLabs) for emotional range.
  • Community voice packs vary; official model focuses on a smaller voice set.

What Kokoro TTS does

  • Apache 2.0 open-source TTS model (82M params)
  • ~100x real-time generation
  • English-focused with 8 languages in community builds
  • Runs locally, on CPU/GPU, or via free hosted demos
  • Downloadable audio, live streaming output

Evaluation guide

Step-by-step evaluation guides for Kokoro TTS — workflow fit, pricing, rights, and a same-input test before paying.

Compare Kokoro TTS with alternatives

Side-by-side pages that weigh Kokoro TTS against overlapping tools on the same five fields.

Where Kokoro TTS appears

Best-of lists and roundups that include Kokoro TTS.

Official sources

These links are retained beside the catalog record so changing details can be rechecked.