dia · Issues· 91 open
Open on GitHubLocally synced open issues (discussions stay on GitHub)
- #37
Adding support for this to run on Apple silicon.
bugduplicateUpdated Aug 26, 2026 - #297
Feature: Use SenseVoice/FunASR for training data annotation
Updated Jul 14, 2026 - #283
MLX Support
Updated Apr 11, 2026 - #294
[Feature request] Permit control of speech rate and add (pause) to nonverbals
Updated Mar 19, 2026 - #136
When running app.py and generating on Mac, an error occurs
Updated Feb 5, 2026 - #291
Inference issues with Dia-1.6B: very short audio, extremely long noisy audio, or no audio output
Updated Jan 4, 2026 - #11
Req to Add support for streaming
plannedUpdated Dec 26, 2025 - #277
How to label the vocal bursts such as <laugh>?
Updated Dec 7, 2025 - #286
gradio 6.x breaks dia - TypeError: BlockContext.__init__() got an unexpected keyword argument 'css'
Updated Dec 5, 2025 - #285
Model not downloading: Entry Not Found error
Updated Nov 27, 2025 - #284
Other audio format supports
Updated Nov 19, 2025 - #280
trying to install on 5070
Updated Nov 17, 2025 - #282
Old Version of Dia Model
Updated Nov 16, 2025 - #281
Error during audio generation or saving: '<' not supported between instances of 'int' and 'NoneType'
Updated Oct 12, 2025 - #271
Microphone bump in audio demos?
Updated Sep 30, 2025