Research engineer at @elevenlabsio. I tweet about ML, audio, creative computing and software engineering.
Trondheim
Joined August 2013
- Tweets363
- Following664
- Followers524
- Likes9K
We proudly present our new v4 text-to-speech model generation! It's the result of a lot of focused work, and I had fun along the way. v4 is an improvement over v3 on many fronts: latency, pronunciation accuracy, naturalness, emotivity and better support for low-resource languages
Introducing Eleven v4 and Eleven v4 Turbo, our fastest and most emotive voice models yet.
Ranked #1 by Artificial Analysis.
Iver Jordal retweeted
Eleven v3 is out of alpha and ready for commercial use.
Since alpha, we've improved stability and accuracy:
- Stability: more reliable model and higher user preference scores
- Accuracy: 68% fewer errors on numbers, symbols, and technical notation
Iver Jordal retweeted
Today we’re introducing Scribe v2: the most accurate transcription model ever released.
While Scribe v2 Realtime is optimized for ultra low latency and agents use cases, Scribe v2 is built for batch transcription, subtitling, and captioning at scale.
Iver Jordal retweeted
Today, we launch the ElevenLabs OSS Engineers Fund - a program that provides sustained support to the open-source projects that help power our work.
Over the next six months, we are contributing $22,000 to projects our engineers rely on.
We just released Scribe v2 Realtime, an industry-leading live speech transcription model 🎉 If you have feedback, my DMs are open
elevenlabs.io/realtime-speec…
Iver Jordal retweeted
Introducing Eleven Music. The highest quality AI music model.
- Complete control over genre, style, and structure
- Multi-lingual, including English, Spanish, German, Japanese and more
- Edit the sound and lyrics of individual sections or the whole song
I just published the world's fastest EBU-compliant audio loudness meter as a Python package. The underlying C++ code was developed and generously open-sourced by Nomono, and has been battle-tested in production for a long time. It is just a `pip install loudness` away!
audiomentations has surpassed 2k stars! I celebrated it by reimplementing Mp3Compression and Limiter in Rust, leading to some nice performance improvements. Also, Python 3.13 is supported now!
The new Limiter implementation is 30% faster, and you can find it here: github.com/iver56/numpy-audi…
The main reason why it is faster is that the delay compensation is done directly in Rust instead of relying on np.pad and slicing.
Iver Jordal retweeted
What makes software development (and engineering) *really* hard instead is:
- Building the right thing (and knowing what this is)
- Coding yourself into a corner (common for juniors - and now also for AI!)
- Architecture
- Tech maturity & risks that come with it
- Testing
- Maintenance
- Migrations
- Real-world edge cases
- Non-functional requirements: eg latency, performance, cost of operations, security
- Compliance
- Tech debt
... and most importantly: people!! (collaboration, conflicts, ownership etc etc)
Iver Jordal retweeted
Very easy way to improve the quality of your work: whenever you put up a PR, take a few seconds to skim through it yourself just as a reviewer would (i.e., in the GitHub UI). I find a surprising number of small issues this way that never stand out in the editor.
numpy-rms now supports Arm64 on Linux, with NEON (SIMD) optimizations. Used the recently launched Github Actions Arm-based runners to build it. Works well.
I just released version 0.35.0 of the data augmentation library audiomentations. New transforms: AddColorNoise, Aliasing and BitCrush. I try to make useful docs, with explanation, visualization, audio examples, code example and API docs, e.g. like this: iver56.github.io/audiomentat…