[opus] Opus 1.5 is now -- with ML

Jean-Marc Valin jmvalin at jmvalin.ca
Mon Mar 4 16:26:15 UTC 2024

Hi everyone,

I'm happy to announce that Opus 1.5 has just been released. Opus 1.5 is 
the first release to make extended use of ML in the encoder and decoder. 
You can read all the details in our demo page at:

Major changes since 1.4 include:
- Significant improvement to packet loss robustness using Deep 
Redundancy (DRED)
- Improved packet loss concealment through Deep PLC
- Low-bitrate speech quality improvements down to 6 kb/s wideband
- Improved x86 (AVX2) and ARM (Neon) optimizations
- Support for 4th and 5th order ambisonics
In addition to the improvements above, this release includes many minor 
bug fixes.

Source code is available at:

Enjoy and please report back any issues.



More information about the opus mailing list