Updated

Kokoro

Small open-weight text-to-speech model (82M parameters) under Apache 2.0, fast enough to run on a CPU or in the browser.

30 open-source projects declare Kokoro in their code; no maker's live product we track uses it yet.

Open sourceSelf-hostable

Profile checked

Ask your AI about this, with this page as the source:ChatGPT ↗Claude ↗Perplexity ↗

How makers use Kokoro

What Kokoro is used for

Speech-to-Text & Text-to-Speech · Open model you run →A small open-weight text-to-speech model that runs on a CPU or in the browser, under Apache 2.0.Trade-off: A fixed set of voices with no cloning, and less expressive than the leading hosted voices.
ElevenLabs135Deepgram65Cartesia29AssemblyAI26Recall.ai21Kokoro0Makers' products on each, for Speech-to-Text & Text-to-Speech

Kokoro vs the alternatives makers chose

OptionMakers' products2026 launchesOpen source
ElevenLabs135 56%63%No
Deepgram65 27%25%No
Cartesia29 12%10%No
AssemblyAI26 11%6%No
Recall.ai21 9%6%No
Fish Audio9 4%5%No
Kokoro0 0%0%Yes

For Speech-to-Text & Text-to-Speech: how many of the 239 makers' products we know the Speech-to-Text & Text-to-Speech of chose each option, and the share among the 80 launched in 2026, since a tool that came first has products from every year.

When to use Kokoro, and when not

Pick Kokoro if

Something else fits better if

  • How the voice sounds is part of the product — narration, characters, content: ElevenLabs or Fish Audio.
  • You're building live conversation where every millisecond of delay shows: Cartesia or Deepgram.
  • Users upload recordings to be transcribed and analysed: AssemblyAI or Deepgram.
  • Your product needs recordings and transcripts from Zoom, Meet or Teams calls: Recall.ai.
  • Voice is a side feature and one vendor matters more than fine control: OpenAI API.
From each decision's guide, written from what makers' products chose and why.

How Kokoro itself is built

1 tools, from its own code, website and Product Hunt page.

Who uses it

No maker's live product on record yet, and 30 open-source projects that declare it in their code.

We haven't found a maker's live product that uses Kokoro yet — only the open-source projects below, which declare it in their code.

FinSynth
FinSynth基于Open WebUI框架的金融大模型交互平台——支持多模态非结构化数据处理Speech-to-Text & Text-to-SpeechIn its code · source ↗
ToolJet
ToolJetOpen-source low-code platform for building internal tools and AI-powered apps on top of…Speech-to-Text & Text-to-SpeechIn its code · source ↗
OGAD
OGADOff Grid AI — private, on-device AI. Run open models (text, vision, image, voice) locall…Speech-to-Text & Text-to-SpeechIn its code · source ↗

Open source: a project that declares Kokoro as a dependency in its public code — verifiable, but not necessarily a live product.

What its projects tell coding agents

15 of the 26 open-source products built with Kokoro that were worked on in the last 180 days keep instruction files for coding agents — 58%, against 53% of all the projects we read. AGENTS.md is in 12, CLAUDE.md in 8.

768words in the median file
uvthe package manager most named, in 5 of 15 files
53%say how to test a change
Named more in these files than in other projects' — in how many of the 15:
What AGENTS.md files say about other tools →What open-source products tell their coding agents →

Alternatives to Kokoro

All alternatives by situation →

Questions makers ask about Kokoro

What are the alternatives to Kokoro?

For Speech-to-Text & Text-to-Speech, the other options makers' products we track chose most are ElevenLabs (135), Deepgram (65), Cartesia (29), AssemblyAI (26), Recall.ai (21), Fish Audio (9). Open source or self-hostable among them: ElevenLabs, Deepgram, Cartesia, AssemblyAI. Each alternative, with the situation it fits, is on the Kokoro alternatives page.

When should you use Kokoro?

Audio must stay on your servers, or volume makes per-minute pricing add up (Speech-to-Text & Text-to-Speech). Something else fits better if: How the voice sounds is part of the product — narration, characters, content, pick ElevenLabs or Fish Audio; you're building live conversation where every millisecond of delay shows, pick Cartesia or Deepgram.

Is Kokoro open source or self-hostable?

Open source, and you can self-host it. source ↗

Can AI coding agents work with Kokoro?

No llms.txt, official MCP server or CLI found yet.

Who uses Kokoro?

No maker's live product we track yet; 30 open-source projects declare it in their code. source ↗