Open Voice Model Library: TTS, Cloning, ASR | VoiceStudio

OmniVoice
k2-fsa · Speech generation
646 languages
Voice cloningRecorded restrictionsUnresolved review
CosyVoice 3
FunAudioLLM · Speech generation · Opt-in
10 languages5.4 GB
Voice cloningUnresolved review
KittenTTS
KittenML · Speech generation
English0.08 GB
Preset voicesUnresolved review
Kokoro 82M
hexgrad · Speech generation
8 languages
Preset voicesUnresolved review
CSM 1B
Sesame · Speech generation
English
Voice cloningUnresolved review
Qwen3-TTS VoiceDesign
Qwen · Speech generation
10 languages
Voice designUnresolved review
Dia 1.6B
Nari Labs · Speech generation
English
Preset voicesUnresolved review
Chatterbox
Resemble AI · Speech generation
English
Preset voicesUnresolved review
MeloTTS English
Speech generation
English
Preset voicesUnresolved review
OuteTTS 1.0
OuteAI · Speech generation
23 languages
Preset voicesRecorded restrictionsUnresolved review
VoxCPM2
OpenBMB · Speech generation
30 languages
Voice cloningVoice designUnresolved review
MOSS-TTS-Nano
OpenMOSS · Speech generation
20 languages
Voice cloningUnresolved review
MOSS-TTS v1.5
OpenMOSS · Speech generation · Opt-in
31 languages16 GB
Voice cloningUnresolved review
GPT-SoVITS
RVC-Boss · Speech generation
5 languages
Voice cloningBring your own serverUnresolved review
Sherpa-ONNX TTS
k2-fsa · Speech generation
Languages vary
Preset voicesUnresolved review
IndexTTS 2.5
Bilibili · Speech generation · Opt-in
5 languages
Voice cloningEmotion controlUnresolved review
Supertonic-3
Supertone · Speech generation
31 languages0.4 GB
Preset voicesUnresolved review
dots.tts
rednote-hilab · Speech generation · Opt-in
24 languages9 GB
Voice cloningUnresolved review
Confucius4-TTS
NetEase Youdao · Speech generation · Opt-in
14 languages5 GB
Voice cloningUnresolved review
PocketTTS
Kyutai · Speech generation
6 languages0.1 GB
Voice cloningUnresolved review
Breeze-TTS-2
BreezeBlue · Speech generation · Opt-in
2 languages4.73 GB
Voice cloningVoice designUnresolved review
Whisper
OpenAI · Transcription
90+ languages
Word timestampsUnresolved review
Parakeet TDT v3
NVIDIA · Transcription
25 languages1.2 GB
Word timestampsUnresolved review
Moonshine
Useful Sensors · Transcription · Opt-in
English
Unresolved review
FunASR SenseVoice
Alibaba DAMO · Transcription · Opt-in
50+ languages
Speaker labelsUnresolved review
Sherpa-ONNX Dictation
k2-fsa · Transcription
90+ languages0.104 GB
Live dictationUnresolved review
OpenAI-compatible ASR
Transcription · Opt-in
Languages vary
Bring your own serverUnresolved review

GitHub · 0834c8b

Quick answers

Is it really free?
The desktop app is open source under AGPL-3.0, so yes. Pro and Lifetime are a separate build with a paid Commercial License and extra features, for teams that need commercial terms.
Licence guide
Does it phone home?
The free app needs no account or cloud, and goes online when you ask it to: checking for updates or downloading a model. Pro needs an account and sends licence and usage data.
Privacy
Do I need a fancy GPU?
Nope. About 8 GB of RAM is enough to start. A GPU just makes everything faster.
System needs
Can I clone any voice?
Only with the owner's say-so. Impersonation and fraud are off the table.
The rules
Changed my mind. Refund?
7 days, full refund, no questions asked. Direct Pro doesn't renew automatically.
Refund policy
Where do I get help?
Write to us or open an issue. Real inboxes, answered within two business days.
Contact