OpenVoice (MyShell)

by MyShell

MyShell's open-source voice cloning with tone-color extraction.

Looking at OpenVoice (MyShell)? Try this first.

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

TL;DR

Best for self-hosters needing voice cloning with cross-lingual style transfer under a permissive license. Pricing: free (MIT for V1, commercial-allowed for V2).

Category
Open source
License
MIT
Stars
★ 37.1k
Last push
2025-04-19
Pricing
free (MIT for V1, commercial-allowed for V2)
Platforms
Linux, macOS

What it is

OpenVoice is MyShell's open-source TTS model with explicit tone-color cloning and style controls. V1 is MIT-licensed; V2 added cross-lingual cloning across 6+ languages. Used widely as a free alternative to XTTS. Consent posture: open weights — operator-side enforcement.

Best for: Self-hosters needing voice cloning with cross-lingual style transfer under a permissive license.
Watch out for: Output quality below XTTS / ElevenLabs on long-form prosody; V1 is MIT, V2 weights have a separate license.

Install / use

pip install openvoice

Features

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

Links

GitHub repo ↗

OpenVoice (MyShell) vs Whipscribe

FeatureOpenVoice (MyShell)Whipscribe
CategoryOpen sourceTranscription APIs
Pricingfree (MIT for V1, commercial-allowed for V2)$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, macOSWeb, API, MCP

Alternatives to OpenVoice (MyShell)

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.