MeloTTS

by MyShell

High-quality multi-lingual TTS from MyShell — fast and CPU-friendly.

Looking at MeloTTS? Try this first.

Drop your audio. Transcript in seconds. First transcript free, then $4 = 300 min

TL;DR

Best for embedded / edge use cases that need decent multi-language TTS on CPU without cloning. Pricing: free (MIT).

Category
Open source
License
MIT
Stars
★ 7.6k
Last push
2024-12-24
Pricing
free (MIT)
Platforms
Linux, macOS, Windows

What it is

MeloTTS is a lighter sibling of OpenVoice from MyShell. Fast CPU inference, multi-lingual (English, Spanish, French, Chinese, Japanese, Korean), MIT-licensed. Consent posture: synthetic speakers only — no cloning capability.

Best for: Embedded / edge use cases that need decent multi-language TTS on CPU without cloning.
Watch out for: No voice cloning surface — preset speakers only.

Install / use

pip install melotts

Features

Speaker diarizationNo
Word-level timestampsNo
Streaming / real-timeNo
Languages supported6
HIPAA eligibleNo

Links

GitHub repo ↗

MeloTTS vs Whipscribe

FeatureMeloTTSWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfree (MIT)$4–$24 one-time packs (credits never expire) · $2 single unlock · 60 min free on signup
Speaker diarization—Yes
Word timestamps—Yes
Streaming—No
Languages699
PlatformsLinux, macOS, WindowsWeb, API, MCP

Alternatives to MeloTTS

OpenAI Whisper
OpenAI

The reference open-source multilingual ASR model from OpenAI.

OSS · MIT ★ 107.0k
whisper.cpp
Georgi Gerganov

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

OSS · MIT ★ 52.8k
faster-whisper
SYSTRAN

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

OSS · MIT ★ 24.8k

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.