Whisper.cpp. Convert speech to text on your own computer, without sending audio to the internet.

github.com/ggerganov/tmp2

Problem

The full read on this project is a sign-in away — what it solves, who it serves, and where it sits in the market.

Audience

The full read on this project is a sign-in away — what it solves, who it serves, and where it sits in the market.

Market

The full read on this project is a sign-in away — what it solves, who it serves, and where it sits in the market.

Pricing

The full read on this project is a sign-in away — what it solves, who it serves, and where it sits in the market.

Vaya's read on this project

Problem, audience, market, and the verdict — sign in to see it.

Updates

May 2026

cont : add manual trigger for build.yml May 31
ci : remove bindings-java job from release.yml May 31
ci : split release jobs into release.yml May 31
ci : split self-hosted GPU jobs into build-self-hosted.yml May 31
ci : add ccache clear action May 31
ci : fix self-hosted paths to mnt May 31
pi : add config May 31
ci : remove obsolete self-hosted label May 31
common : pass sample rate to `ffmpeg_decode_audio()` May 31
common : re-implement `ffmpeg-transcode.cpp` + clarify ffmpeg usage (… May 31
cuda : disables launch_fattn PDL enrollment due to compiler bug (llam… May 29
mmvq Optim: add MMVQ_PARAMETERS_TURING(mmvq_parameter_table_id) for …… May 29
ggml: auto apply iGPU flag CUDA/HIP if integrated device (llama/23007) May 29
opencl: move backend info printing into its own function (llama/23702) May 29
talk-llama : sync llama.cpp May 29
ggml : bump version to 0.13.1 (ggml/1523) May 29
sync : ggml May 29
meta : Add missing `buffer` set in allreduce fallback !COMPUTE clear … May 29
hexagon: basic/generic op fusion support and RMS_NORM+MUL fusion (lla… May 29
sync : ggml May 29