hylozoik
Well-Known Member
- Registriert
- 21. Dezember 2010
- Beiträge
- 24.252
Ja, das gibt's auch inzwischen - His Her Masters Voice sozusagen ...
![Gitarre :gitarre: :gitarre:](https://images.denkforum.at/smilies/guitar.gif)
Audio-KI "Bark" erzeugt natürliche Sprache und kann sogar singen
www.heise.de
github.com
https://suno.com/ | https://suno.com/about
Ein Erstversuch mit Erich Kästner Gedichten als ''Lyrics'' ...![Big Grin :D :D](https://cdn.jsdelivr.net/joypixels/assets/8.0/png/unicode/64/1f600.png)
![Cool :cool: :cool:](https://cdn.jsdelivr.net/joypixels/assets/8.0/png/unicode/64/1f60e.png)
suno.com
suno.com
suno.com
suno.com
suno.com
![Romeo :romeo: :romeo:](https://images.denkforum.at/smilies/romeo.gif)
![Trommel :trommel: :trommel:](https://images.denkforum.at/smilies/drummer.gif)
![Gitarre :gitarre: :gitarre:](https://images.denkforum.at/smilies/guitar.gif)
Audio-KI "Bark" erzeugt natürliche Sprache und kann sogar singen
![www.heise.de](/proxy.php?image=https%3A%2F%2Fheise.cloudimg.io%2Fbound%2F1200x1200%2Fq85.png-lossy-85.webp-lossy-85.foil1%2F_www-heise-de_%2Fimgs%2F18%2F4%2F1%2F4%2F8%2F3%2F6%2F5%2FA_comic_dog_holding_a_megaphone_in_one_paw_and_making_an_03b40c13-5410-418f-8c21-e9d23e9ce666-7727ea0c0d7c11e6.png&hash=37ff5dad829f0b8a32daa1673f696d04&return_error=1)
Audio-KI "Bark" erzeugt natürliche Sprache und kann sogar singen
Die Audio-KI "Bark" von Suno AI verspricht realistische, multilinguale Sprachausgabe inklusive Gesang und Umgebungsgeräuschen. Bellen kann Bark aber noch nicht.
Die generative Audio-KI Bark von Suno AI aus Cambridge erzeugt aus Textprompts natürlich klingende Sprache – auch als Gesang. Der Text-zu-Audio-Generator versteht momentan 13 Sprachen, die man in einem Prompt mischen kann. Ferner interpretiert Bark verschiedene Regieanweisungen wie "[laughs]", "[gasps]" oder "[sighs]".
GitHub - suno-ai/bark: 🔊 Text-Prompted Generative Audio Model
🔊 Text-Prompted Generative Audio Model. Contribute to suno-ai/bark development by creating an account on GitHub.
Bark is fully generative text-to-audio model devolved for research and demo purposes. It follows a GPT style architecture similar to AudioLM and Vall-E and a quantized Audio representation from EnCodec. It is not a conventional TTS model, but instead a fully generative text-to-audio model capable of deviating in unexpected ways from any given script. Different to previous approaches, the input text prompt is converted directly to audio without the intermediate use of phonemes. It can therefore generalize to arbitrary instructions beyond speech such as music lyrics, sound effects or other non-speech sounds.
Below is a list of some known non-speech sounds, but we are finding more every day. Please let us know if you find patterns that work particularly well on Discord!
- [laughter]
- [laughs]
- [sighs]
- [music]
- [gasps]
- [clears throat]
- — or ... for hesitations
- ♪ for song lyrics
- CAPITALIZATION for emphasis of a word
- [MAN] and [WOMAN] to bias Bark toward male and female speakers, respectively
https://suno.com/ | https://suno.com/about
We are a team of musicians and artificial intelligence experts based in Cambridge, MA. We are proud alumni of pioneering tech companies like Meta, TikTok and Kensho, where our founding team worked together before starting Suno.
We like to ship code, make music and drink coffee.
Ein Erstversuch mit Erich Kästner Gedichten als ''Lyrics'' ...
![Big Grin :D :D](https://cdn.jsdelivr.net/joypixels/assets/8.0/png/unicode/64/1f600.png)
![Cool :cool: :cool:](https://cdn.jsdelivr.net/joypixels/assets/8.0/png/unicode/64/1f60e.png)
![suno.com](/proxy.php?image=https%3A%2F%2Fcdn2.suno.ai%2Fimage_45a38df2-cc07-41d5-b1ca-2b06d402c0ec.jpeg&hash=905bd629dd162b45ec1dd54ffb46b323&return_error=1)
Kaestner @ KI Music Think Positive 001 by @hylozoik | Suno
jazz bebop cool bossa samba vocal a capella man woman chorus funky song. Listen and make your own with Suno.
![suno.com](/proxy.php?image=https%3A%2F%2Fcdn2.suno.ai%2Fimage_e113c256-7b29-46fc-99a5-089d70f1d61f.jpeg&hash=e6813d4bfc835dff843851f06540a88e&return_error=1)
Kaestner @ KI Music 004 by @hylozoik | Suno
jazz bebop fusion clarinet cool scat vocal a capella man woman chorus funky guitar piano bass [sighs] song. Listen and make your own with Suno.
![suno.com](/proxy.php?image=https%3A%2F%2Fcdn2.suno.ai%2Fimage_ad8211a6-4a3a-4041-b350-fecf62a4ae3a.jpeg&hash=bf0eee05c85464eeda1bed082203bd84&return_error=1)
Kaestner @ KI Music 003 by @hylozoik | Suno
jazz bebop fusion clarinet cool scat vocal a capella man woman chorus funky guitar piano bass [sighs] song. Listen and make your own with Suno.
![suno.com](/proxy.php?image=https%3A%2F%2Fcdn2.suno.ai%2Fimage_5025e8e6-5ffa-4186-b464-61436e0af1b2.jpeg&hash=2273e2c93a27da7d59b687fdc6324675&return_error=1)
Kaestner @ KI Music Mai 2024 by @hylozoik | Suno
bebop hardbop fusion low voice baroque cool scat acapella man + woman + kids mix choir funk jazz piano bass [sighs] song. Listen and make your own with Suno.
![suno.com](/proxy.php?image=https%3A%2F%2Fcdn2.suno.ai%2Fimage_baa9f4f1-5fd0-4ad6-81f6-b303f36cf5a9.jpeg&hash=f74bd21d17de3be32e591233c6b5ac07&return_error=1)
Kaestner @ KI Music Mai Swing by @hylozoik | Suno
bebop hardbop fusion low voice baroque cool scat acapella man + woman + kids mix choir funk jazz piano bass [sighs] song. Listen and make your own with Suno.
![suno.com](/proxy.php?image=https%3A%2F%2Fcdn1.suno.ai%2FSuno-Avatar-1080x1080.png&hash=f483afbef1e4f7755ce2a53a1a15379a&return_error=1)
Zuletzt bearbeitet: