github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #5451] Speech-To-Text Transcription #65444

New Issue
Closed
opened 2026-05-03 21:18:10 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-05-03 21:18:10 -05:00
Owner
Copy Link

Originally created by @HerroHK on GitHub (Jul 3, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5451

Issue: our company has audio recordings that are confidential in nature. We have setup a linux server (Ubuntu) running Ollama with both Open-WebUI and AnythingLLM as interface. However, it seems both are not able to transcribe long (up to 8 hours) audio recordings, and we only get back snippets. It is also unclear where the boundaries are in terms of time, as it seems some parts do get translated.

It would make a great addition to Ollama if we could make use of Whisper or other models locally to do this.

I am pretty sure it is a very common use-case of AI, with plenty of "commercially available options". But it is mostly that we can't use commercial services easily to fullfill our needs and contracts at the same time.

Thanks for considering this.

Originally created by @HerroHK on GitHub (Jul 3, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5451 Issue: our company has audio recordings that are confidential in nature. We have setup a linux server (Ubuntu) running Ollama with both Open-WebUI and AnythingLLM as interface. However, it seems both are not able to transcribe long (up to 8 hours) audio recordings, and we only get back snippets. It is also unclear where the boundaries are in terms of time, as it seems some parts do get translated. It would make a great addition to Ollama if we could make use of Whisper or other models locally to do this. I am pretty sure it is a very common use-case of AI, with plenty of "commercially available options". But it is mostly that we can't use commercial services easily to fullfill our needs and contracts at the same time. Thanks for considering this.
GiteaMirror added the feature request label 2026-05-03 21:18:10 -05:00
GiteaMirror commented 2026-05-03 21:18:13 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Jul 3, 2024):

@HerroHK Thanks for the issue. Definitely something we'd like to add at some point. I'm going to close this though as a dupe of #3265. There's also #1234 for Text-to-Speech.

<!-- gh-comment-id:2206760049 --> @pdevine commented on GitHub (Jul 3, 2024): @HerroHK Thanks for the issue. Definitely something we'd like to add at some point. I'm going to close this though as a dupe of #3265. There's also #1234 for Text-to-Speech.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label feature request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#65444
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?