Our great sponsors
-
StarGANv2-VC
StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion
-
WorkOS
The modern identity platform for B2B SaaS. The APIs are flexible and easy-to-use, supporting authentication, user identity, and complex enterprise features like SSO and SCIM provisioning.
-
tt-vae-gan
Timbre transfer with variational autoencoding and cycle-consistent adversarial networks. Able to transfer the timbre of an audio source to that of another.
This looks like it was previously known as Vocodes, made by echelon who is here on HN:
https://news.ycombinator.com/item?id=23965787
The code repos used are listed in their credits section, and it looks like a mixture of (customised?) Tacotron2, Glow-TTS, HifGan, and others. Videos are generated using Wav2Lip.
Text-To-Speech (TTS) has improved greatly over the past several years, but there's still a lot of metallic sounds in "pure" TTS implementations. I've started exploring voice style conversion, otherwise known as "voice cloning", and there are some interesting repos out there with decent results. These work differently from TTS, in that you don't type out the text to be spoken, but rather pass in an audio file of what you want the cloned speaker to say, and the system outputs an audio file with the same sounds (words, intonation) but with a different speaker identity.
This may be easier to get the right cadence and emotion in the generated audio, as text doesn't capture proper emotion and intonation. I suspect game character audio will use more of voice-style conversion instead of pure TTS simply to get the right emotional cadence of the lines being delivered.
Some interesting voice style conversion repos (in no order, just a random selection if anyone is interested in exploring):
https://github.com/yl4579/StarGANv2-VC
JukeBox did that for music so it's not impossible ... https://openai.com/blog/jukebox/
Related posts
- Will AI be able to create similar sounding music based off input?
- Best model for music generation?
- Where can I find more info on the various model files
- Why didn't OpenAI MIT license Jukebox the same way they did CLIP?
- [R] [N] Noise2Music - Diffusion models for generating high quality music audio from text prompts, by Google Research