eSpeak NG

by eSpeak NG community

Compact open-source TTS for 100+ languages — the embedded workhorse.

TL;DR

Compact open-source TTS for 100+ languages — the embedded workhorse.

Best for accessibility / screen readers (Orca, NVDA) and embedded systems where size matters more than quality. Pricing: free (GPL-3.0).

Category
Open source
License
—
Stars
—
Last push
—
Pricing
free (GPL-3.0)
Platforms
Linux, macOS, Windows

What it is

eSpeak NG is the maintained fork of eSpeak — a tiny formant-synthesis TTS engine supporting 100+ languages. The default backend for NVDA on Windows and Orca on Linux. Sub-megabyte footprint. GPL-3.0. Consent posture: synthetic-only by design.

Best for: Accessibility / screen readers (Orca, NVDA) and embedded systems where size matters more than quality.
Watch out for: Formant-synthesis — robotic by design, not natural-sounding.

Install / use

sudo apt install espeak-ng

Features

Speaker diarizationNo
Word-level timestampsNo
Streaming / real-timeNo
Languages supported100
HIPAA eligibleNo

eSpeak NG vs Whipscribe

FeatureeSpeak NGWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfree (GPL-3.0)free beta
Speaker diarization—Yes
Word timestamps—Yes
Streaming—No
Languages10099
PlatformsLinux, macOS, WindowsWeb, API, MCP

Alternatives to eSpeak NG

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.