Currently text to speech is supported and the output is cached in fragments.
It would be useful if the UI presented an option to download the generated speech as a single MP3 file.
Originally created by @cduk on GitHub (Aug 28, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/4991
Currently text to speech is supported and the output is cached in fragments.
It would be useful if the UI presented an option to download the generated speech as a single MP3 file.
There is an ElevenLabs TTS Function available on the Open WebUI community website that you can import directly into your Open WebUI instance. Once configured, you can directly download auto of generated Text-To-Speech.
<!-- gh-comment-id:2315967799 -->
@silentoplayz commented on GitHub (Aug 28, 2024):
There is an ElevenLabs TTS Function available on the Open WebUI community website that you can import directly into your Open WebUI instance. Once configured, you can directly download auto of generated Text-To-Speech.
https://openwebui.com/f/justinrahb/elevenlabs_tts/
Thanks. Does this work only with ElevenLabs generated TTS samples? I currently use an OpenAI compatible audio endpoint which points to a custom server.
<!-- gh-comment-id:2315998791 -->
@cduk commented on GitHub (Aug 28, 2024):
Thanks. Does this work only with ElevenLabs generated TTS samples? I currently use an OpenAI compatible audio endpoint which points to a custom server.
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @cduk on GitHub (Aug 28, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/4991
Currently text to speech is supported and the output is cached in fragments.
It would be useful if the UI presented an option to download the generated speech as a single MP3 file.
@silentoplayz commented on GitHub (Aug 28, 2024):
There is an ElevenLabs TTS Function available on the Open WebUI community website that you can import directly into your Open WebUI instance. Once configured, you can directly download auto of generated Text-To-Speech.
https://openwebui.com/f/justinrahb/elevenlabs_tts/
@cduk commented on GitHub (Aug 28, 2024):
Thanks. Does this work only with ElevenLabs generated TTS samples? I currently use an OpenAI compatible audio endpoint which points to a custom server.