Kokoro TTS

by hexgrad (research)

Lightweight 82M-param open-source TTS — Apache-2.0, runs on a Raspberry Pi.

TL;DR

Lightweight 82M-param open-source TTS — Apache-2.0, runs on a Raspberry Pi.

Best for edge / on-device TTS where you need decent quality at 82M parameters. Pricing: free (Apache-2.0).

Category
Open source
License
—
Stars
—
Last push
—
Pricing
free (Apache-2.0)
Platforms
Linux, macOS, Windows

What it is

Kokoro is a permissively-licensed 82M-parameter TTS model that punches above its weight on the MOS leaderboard for its size. Apache-2.0 license. Consent posture: synthetic-only.

Best for: Edge / on-device TTS where you need decent quality at 82M parameters.
Watch out for: Synthetic voices only — no cloning surface in the public model.

Install / use

pip install kokoro

Features

Speaker diarizationNo
Word-level timestampsNo
Streaming / real-timeNo
Languages supported8
HIPAA eligibleNo

Kokoro TTS vs Whipscribe

FeatureKokoro TTSWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfree (Apache-2.0)free beta
Speaker diarization—Yes
Word timestamps—Yes
Streaming—No
Languages899
PlatformsLinux, macOS, WindowsWeb, API, MCP

Alternatives to Kokoro TTS

OpenAI Whisper
OpenAI

The reference open-source multilingual ASR model from OpenAI.

OSS · MIT ★ 98.1k
whisper.cpp
Georgi Gerganov

C/C++ port of Whisper — runs on anything, from a Raspberry Pi to Apple Silicon.

OSS · MIT ★ 48.8k
faster-whisper
SYSTRAN

4× faster than reference Whisper using CTranslate2 — production sweet spot.

OSS · MIT ★ 22.3k

Whipscribe is a managed faster-whisper + whisperX service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.