Main Page

Welcome to OpenVoice-Tech Wiki

A place for everyone sharing passion and knowledge for open voice technology.

Open across all voice projects

We currently have 286 pages and 23 registered users here.

But a wiki for all open voice enthusiasts cannot be driven by one person alone. Do you like the idea of this site?

Please help by sharing your thoughts and/or add more information/pages.

5 newest articles

1. Portuguese
2. Kokoro TTS
3. Terminology
4. First steps
5. Piper TTS

What's planned

Following things are planned to come.

• Technical information, best-practice, lessons-learned about STT, TTS, open voice assistants
• Voice related paper information and discussion
• Newsticker with voice related announcements
• any more ideas? Let's discuss here

Available categories

Open Voice Tech

Dataset

Hardware related

HelloWorld

Language

Lessons learned

Open Voice Assistants

Paper discussion

Project

STT

TTS

Videos

Voice datasets

Glossary of voice tech

OVT:What is OpenVoice-Tech Wiki

Want to contribute to the Wiki?

That's great, thanks for your support.

Requested articles that should be created:

1. Intent (2 links)
2. Pytorch (2 links)
3. Tensorflow (2 links)
4. Alignment (1 link)
5. Batch size (1 link)
6. Chatbots (1 link)
7. Checkpoint (1 link)
8. Command-and-control (1 link)
9. Continue Coqui TTS training based on checkpoint (1 link)
10. Deep learning (1 link)
11. Deepspeech (1 link)
12. Dialog manager (1 link)
13. Epoch (1 link)
14. Espeak (1 link)
15. Finetune existing Coqui TTS model (1 link)
16. GPT-3 (1 link)
17. Home-automation (1 link)
18. Homophon (1 link)
19. Hotword (1 link)
20. Howl (1 link)
21. Human-in-the-loop (1 link)
22. IBM Watson (1 link)
23. Inference (1 link)
24. Instant-messaging (1 link)
25. Internationale Phonetische Alphabet (1 link)
26. Lautsprache (1 link)
27. Learning rate (1 link)
28. Liste der IPA-Zeichen (1 link)
29. Machine learning (1 link)
30. Mimic-Recording-Studio (1 link)
31. Mixed-initiative (1 link)
32. Model (1 link)
33. Mycroft in French (1 link)
34. Mycroft in Spanish (1 link)
35. OVT:Construction Area (1 link)
36. Phonemes (1 link)
37. Repository (1 link)
38. Scribosermo (1 link)
39. Snowboy (1 link)
40. Speaker (1 link)
41. Speaker identification (1 link)
42. Step (1 link)
43. Thorsten voice (1 link)
44. Transcoding (1 link)
45. Utterance (1 link)
46. Voice print (1 link)
47. Voicebots (1 link)
48. WWvW (1 link)
49. Word error rate (1 link)

List articles here you would like to see here:

• Using Thorsten (2020) DCA model with Coqui
• Using Thorsten (2021) Forward Tacotron Model
• Add your own requests here

Links to open voice projects

Feel free to check following links:

• Coqui STT/TTS on Github
• Mycroft AI voice assistant on Github
• Women in voice
• Rhasspy voice assistant on Github
• SEPIA voice assistant on Github
• Link collection to opensource voice projects by Kathy Reid
• Website "Thorsten - Open German Voice Dataset"