# whisper.cpp changelog

> Port of OpenAI's Whisper speech recognition in C/C++.

- Vendor: ggml
- Category: AI
- Official site: https://github.com/ggml-org/whisper.cpp
- Tracked by: What's New (https://whatsnew.fyi/product/whisper-cpp)
- Harvested from: GitHub (ggml-org/whisper.cpp)
- Entries below: 10 (newest first)

What's New is an index, not a publisher: every entry below links to the vendor's own release notes, which are the authoritative source. Entries are labelled where they are hand-curated sample data, pre-releases, or drawn from a secondary source such as a developer blog.

## Releases

### v1.9.2

- Date: 2026-08-04
- Version: v1.9.2
- Original notes: https://github.com/ggml-org/whisper.cpp/releases/tag/v1.9.2
- Permalink: https://whatsnew.fyi/product/whisper-cpp/releases/v1.9.2

- **fixed** — Fix pkgconfig configuration for Nix build
- **fixed** — Fix argument flag for min speech duration in VAD
- **fixed** — Fix VAD min silence argument parsing
- **fixed** — Remove leading space from txt output
- **added** — Include parakeet in build-xcframework.sh
- **added** — Expose internal VAD speech segments
- **added** — Add VAD speech segments API to ruby bindings
- **changed** — Make voice_length() utf-8 aware for CJK
- **changed** — Map token timestamps to original time when VAD is enabled
- **changed** — Improve inference performance of Android example project
- **changed** — Verify hparams loaded from parakeet model bin file

##### What's Changed
* sync : ggml by @ggerganov in https://github.com/ggml-org/whisper.cpp/pull/3896
* include parakeet in build-xcframework.sh by @daaku in https://github.com/ggml-org/whisper.cpp/pull/3899
* Fix pkgconfig configuration (Nix build failure) by @nmouha in https://github.com/ggml-org/whisper.cpp/pull/3894
* examples : update model names in parakeet-cli README.md [no ci] by @danbev in https://github.com/ggml-org/whisper.cpp/pull/3906
* examples: Fix argument flag for min speech duration in VAD by @QuantiusBenignus in https://github.com/ggml-org/whisper.cpp/pull/3907
* sync : ggml by @ggerganov in https://github.com/ggml-org/whisper.cpp/pull/3912
* examples : Improved inference performance of Android example project by @yymin1022 in https://github.com/ggml-org/whisper.cpp/pull/3913
* ci : set GGML_NATIVE=OFF for sanitize builds by @danbev in https://github.com/ggml-org/whisper.cpp/pull/3920
* whisper : make voice_length() utf-8 aware for CJK by @buxuku in https://github.com/ggml-org/whisper.cpp/pull/3915
* whisper : map token timestamps to original time when VAD is enabled by @buxuku in https://github.com/ggml-org/whisper.cpp/pull/3910
* ci, examples : add package-lock.json to examples addon node by @danbev in https://github.com/ggml-org/whisper.cpp/pull/3919
* whisper : expose internal VAD speech segments by @buxuku in https://github.com/ggml-org/whisper.cpp/pull/3916
* sync : ggml by @ggerganov in https://github.com/ggml-org/whisper.cpp/pull/3940
* Fix #587: Remove leading space from txt output by @JingliangGao in https://github.com/ggml-org/whisper.cpp/pull/3921
* ruby : add VAD speech segments API by @KitaitiMakoto in https://github.com/ggml-org/whisper.cpp/pull/3931
* Adding ruby bindings change log by @taf2 in https://github.com/ggml-org/whisper.cpp/pull/3959
* verify hparams loaded from parakeet model bin file by @bhargav191098 in https://github.com/ggml-org/whisper.cpp/pull/3950
* sync : ggml by @ggerganov in https://github.com/ggml-org/whisper.cpp/pull/3962
* Fix VAD min silence argument parsing by @chupakobra6 in https://github.com/ggml-org/whisper.cpp/pull/3963
* ci : set GGML_NATIVE=OFF for build-vad workflow by @danbev in https://github.com/ggml-org/whisper.cpp/pull/3966
* sync : ggml by @ggerganov in https://github.com/ggml-org/whisper.cpp/pull/3969
* release : v1.9.2 by @danbev in https://github.com/ggml-org/whisper.cpp/pull/3970

##### New Contributors
* @daaku made their first contribution in https://github.com/ggml-org/whisper.cpp/pull/3899
* @nmouha made their first contribution in https://github.com/ggml-org/whisper.cpp/pull/3894
* @QuantiusBenignus made their first contribution in https://github.com/ggml-org/whisper.cpp/pull/3907
* @yymin1022 made their first contribution in https://github.com/ggml-org/whisper.cpp/pull/3913
* @JingliangGao made their first contribution in https://github.com/ggml-org/whisper.cpp/pull/3921
* @bhargav191098 made their first contribution in https://github.com/ggml-org/whisper.cpp/pull/3950
* @chupakobra6 made their first contribution in https://github.com/ggml-org/whisper.cpp/pull/3963

**Full Changelog**: https://github.com/ggml-org/whisper.cpp/compare/v1.9.1...v1.9.2

### v1.9.1

- Date: 2026-06-19
- Version: v1.9.1
- Original notes: https://github.com/ggml-org/whisper.cpp/releases/tag/v1.9.1
- Permalink: https://whatsnew.fyi/product/whisper-cpp/releases/v1.9.1

- **changed** — Add GGML_NATIVE=OFF and GGML_BMI2=OFF to windows-blas CI configuration

##### What's Changed
* ci : add GGML_NATIVE=OFF and GGML_BMI2=OFF to windows-blas by @danbev in https://github.com/ggml-org/whisper.cpp/pull/3891
* release : v1.9.1 by @danbev in https://github.com/ggml-org/whisper.cpp/pull/3892


**Full Changelog**: https://github.com/ggml-org/whisper.cpp/compare/v1.9.0...v1.9.1

### v1.9.0

- Date: 2026-06-17
- Version: v1.9.0
- Original notes: https://github.com/ggml-org/whisper.cpp/releases/tag/v1.9.0
- Permalink: https://whatsnew.fyi/product/whisper-cpp/releases/v1.9.0

- **added** — Add support for NVIDIA Parakeet
- **added** — Add Parakeet support for Ruby bindings

##### What's Changed
* ci : only trigger release jobs for tags by @danbev in https://github.com/ggml-org/whisper.cpp/pull/3883
* parakeet : add support for NVIDIA Parakeet by @danbev in https://github.com/ggml-org/whisper.cpp/pull/3735
* ruby : add support for Parakeet by @KitaitiMakoto in https://github.com/ggml-org/whisper.cpp/pull/3885
* release : v1.9.0 by @danbev in https://github.com/ggml-org/whisper.cpp/pull/3886


**Full Changelog**: https://github.com/ggml-org/whisper.cpp/compare/v1.8.7...v1.9.0

### v1.8.7

- Date: 2026-06-16
- Version: v1.8.7
- Original notes: https://github.com/ggml-org/whisper.cpp/releases/tag/v1.8.7
- Permalink: https://whatsnew.fyi/product/whisper-cpp/releases/v1.8.7

- **changed** — Do not assume /usr/lib library installation
- **fixed** — Server merges split UTF-8 token text in verbose JSON
- **fixed** — Catch C++ exceptions in whisper_init_with_params_no_state
- **fixed** — CoreML fix --quantize crash and --optimize-ane label for mlprogram format
- **added** — Add --version flag to CLI

##### What's Changed
* Do not assume /usr/lib library installation. by @waptaff in https://github.com/ggml-org/whisper.cpp/pull/3693
* server : merge split UTF-8 token text in verbose JSON by @lyonsno in https://github.com/ggml-org/whisper.cpp/pull/3850
* whisper : catch C++ exceptions in whisper_init_with_params_no_state by @danscMax in https://github.com/ggml-org/whisper.cpp/pull/3831
* ci : refactor + optimize by @ggerganov in https://github.com/ggml-org/whisper.cpp/pull/3847
* ci : only publish/push docker images daily by @danbev in https://github.com/ggml-org/whisper.cpp/pull/3854
* ci : use ccache instead of sccache for windows-cublas [no ci] by @danbev in https://github.com/ggml-org/whisper.cpp/pull/3855
* ci : pin github actions to commit SHAs by @danbev in https://github.com/ggml-org/whisper.cpp/pull/3856
* ci : use emscripten-core and pin version by @danbev in https://github.com/ggml-org/whisper.cpp/pull/3857
* ci:  build-windows action slimming by @danbev in https://github.com/ggml-org/whisper.cpp/pull/3858
* Ci build quantize vad wasm ccache by @danbev in https://github.com/ggml-org/whisper.cpp/pull/3860
* ci : add HF_TOKEN to docker.yml workflow [no ci] by @danbev in https://github.com/ggml-org/whisper.cpp/pull/3861
* ci : add ccache to build-sycl [no ci] by @danbev in https://github.com/ggml-org/whisper.cpp/pull/3859
* sync : ggml by @ggerganov in https://github.com/ggml-org/whisper.cpp/pull/3867
* coreml : fix --quantize crash and --optimize-ane label for mlprogram format by @krystophny in https://github.com/ggml-org/whisper.cpp/pull/3868
* ci : pin github actions to commit sha's by @danbev in https://github.com/ggml-org/whisper.cpp/pull/3865
* sync : ggml by @ggerganov in https://github.com/ggml-org/whisper.cpp/pull/3880
* cli : add `--version` flag by @rumitvn in https://github.com/ggml-org/whisper.cpp/pull/3878
* release : v1.8.7 by @danbev in https://github.com/ggml-org/whisper.cpp/pull/3881

##### New Contributors
* @waptaff made their first contribution in https://github.com/ggml-org/whisper.cpp/pull/3693
* @lyonsno made their first contribution in https://github.com/ggml-org/whisper.cpp/pull/3850
* @danscMax made their first contribution in https://github.com/ggml-org/whisper.cpp/pull/3831
* @krystophny made their first contribution in https://github.com/ggml-org/whisper.cpp/pull/3868
* @rumitvn made their first contribution in https://github.com/ggml-org/whisper.cpp/pull/3878

**Full Changelog**: https://github.com/ggml-org/whisper.cpp/compare/v1.8.6...v1.8.7

### v1.8.6

- Date: 2026-06-02
- Version: v1.8.6
- Original notes: https://github.com/ggml-org/whisper.cpp/releases/tag/v1.8.6
- Permalink: https://whatsnew.fyi/product/whisper-cpp/releases/v1.8.6

- **changed** — re-implement ffmpeg-transcode.cpp and clarify ffmpeg usage
- **fixed** — fix path to whisper.h in examples.yml

##### What's Changed
* common : re-implement `ffmpeg-transcode.cpp` + clarify ffmpeg usage by @ggerganov in https://github.com/ggml-org/whisper.cpp/pull/3846
* ci : fix path to whisper.h in examples.yml [no ci] by @danbev in https://github.com/ggml-org/whisper.cpp/pull/3842

**Full Changelog**: https://github.com/ggml-org/whisper.cpp/compare/v1.8.5...v1.8.6

### v1.8.5

- Date: 2026-05-29
- Version: v1.8.5
- Original notes: https://github.com/ggml-org/whisper.cpp/releases/tag/v1.8.5
- Permalink: https://whatsnew.fyi/product/whisper-cpp/releases/v1.8.5

- **fixed** — Fix dangling pointers, memory leak, and SEGV on parallel transcription in Ruby bindings
- **added** — Add streaming detect and explicit state reset to VAD
- **added** — Add support for controlling token_timestamps directly in server
- **fixed** — Fix max_tokens skipping remaining audio issue
- **fixed** — Fix params leak between requests in server
- **fixed** — Fix no_speech_thold not being read in server
- **added** — Add support for carry_initial_prompt in server
- **added** — Return speaker information in JSON in server
- **fixed** — Fix memory leak in read_audio_data in examples
- **changed** — Set bench data for each iteration in whisper
- **fixed** — Fix server /inference failing to decode in-memory audio regression
- **changed** — Merge tokens split across UTF-8 boundaries in JSON output in CLI
- **changed** — Ruby bindings now transcribe without GVL, accept more MemoryViews, and support Windows
- **fixed** — Fix incorrect timestamps

##### Overview

Maintenance release + performance improvements all around:

https://github.com/ggml-org/whisper.cpp/blob/master/scripts/bench-all-gg.txt

##### What's Changed
* ruby : fix dangling pointers, memory leak, and SEGV on parallel transcription by @KitaitiMakoto in https://github.com/ggml-org/whisper.cpp/pull/3715
* sync : ggml by @ggerganov in https://github.com/ggml-org/whisper.cpp/pull/3730
* vad : add streaming detect + explicit state reset by @danielbodart in https://github.com/ggml-org/whisper.cpp/pull/3677
* bench : sync submit-results URL to ggml-org by @jinweihan-ai in https://github.com/ggml-org/whisper.cpp/pull/3769
* sync : ggml by @ggerganov in https://github.com/ggml-org/whisper.cpp/pull/3786
* sync : ggml by @ggerganov in https://github.com/ggml-org/whisper.cpp/pull/3789
* ruby : transcribe without GVL, accept more MemoryViews, Windows support, fix memory size report, improve document by @KitaitiMakoto in https://github.com/ggml-org/whisper.cpp/pull/3775
* Incorrect timestamps by @bviksoe in https://github.com/ggml-org/whisper.cpp/pull/2279
* server: Add support for controlling token_timestamps directly by @alubbe in https://github.com/ggml-org/whisper.cpp/pull/3785
* Fix #984: About max_tokens skipping remaining audio issue by @annaeina in https://github.com/ggml-org/whisper.cpp/pull/3798
* server: Fix params leak between requests by @alubbe in https://github.com/ggml-org/whisper.cpp/pull/3784
* server: Fix no_speech_thold not being read by @alubbe in https://github.com/ggml-org/whisper.cpp/pull/3783
* sync : ggml by @ggerganov in https://github.com/ggml-org/whisper.cpp/pull/3803
* server: Add support for carry_initial_prompt by @alubbe in https://github.com/ggml-org/whisper.cpp/pull/3781
* server: Return speaker information in JSON by @alubbe in https://github.com/ggml-org/whisper.cpp/pull/3782
* examples : fix memory leak in read_audio_data by @petterreinholdtsen in https://github.com/ggml-org/whisper.cpp/pull/3810
* whisper : set bench data for each iteration by @danbev in https://github.com/ggml-org/whisper.cpp/pull/3812
* ci : use github ubuntu-22.04-arm runner instead of qemu by @danbev in https://github.com/ggml-org/whisper.cpp/pull/3815
* fix: server /inference fails to decode in-memory audio (regression) by @ServeurpersoCom in https://github.com/ggml-org/whisper.cpp/pull/3818
* fix: in bindings/ruby/test/jfk_reader/jfk_reader in jfk_reader.c by @orbisai0security in https://github.com/ggml-org/whisper.cpp/pull/3756
* cmake : add CMakePresets.json [no ci] by @danbev in https://github.com/ggml-org/whisper.cpp/pull/3808
* sync : ggml by @ggerganov in https://github.com/ggml-org/whisper.cpp/pull/3824
* [AMD] Add AMD ROCm/HIP GPU build instructions by @Kaihui-AMD in https://github.com/ggml-org/whisper.cpp/pull/3823
* cli : merge tokens split across UTF-8 boundaries in JSON output by @texasich in https://github.com/ggml-org/whisper.cpp/pull/3751
* docs : add AGENTS.md and CONTRIBUTING.md [no ci] by @danbev in https://github.com/ggml-org/whisper.cpp/pull/3826
* ci : only run docker jobs when pushed to master [no ci] by @danbev in https://github.com/ggml-org/whisper.cpp/pull/3828
* ci : set GGML_NATIVE=OFF for bindings-java by @danbev in https://github.com/ggml-org/whisper.cpp/pull/3830
* ci : renable arm64 docker builds by @danbev in https://github.com/ggml-org/whisper.cpp/pull/3832
* ci : add on push/pull_request paths ruby job by @danbev in https://github.com/ggml-org/whisper.cpp/pull/3833
* ci : fix include paths for bindings-go job [no ci] by @danbev in https://github.com/ggml-org/whisper.cpp/pull/3835
* ci : add ignore for bindings/{ruby, go} in build.yml [no ci] by @danbev in https://github.com/ggml-org/whisper.cpp/pull/3837
* sync : ggml by @ggerganov in https://github.com/ggml-org/whisper.cpp/pull/3840

##### New Contributors
* @danielbodart made their first contribution in https://github.com/ggml-org/whisper.cpp/pull/3677
* @jinweihan-ai made their f

_[Truncated at 4000 characters — full notes: https://github.com/ggml-org/whisper.cpp/releases/tag/v1.8.5]_

### v1.8.4

- Date: 2026-03-19
- Version: v1.8.4
- Original notes: https://github.com/ggml-org/whisper.cpp/releases/tag/v1.8.4
- Permalink: https://whatsnew.fyi/product/whisper-cpp/releases/v1.8.4

- **fixed** — Fix UTF-8 character cut off to two replacement characters in segment wrapping (max_len)
- **added** — Add -g/--gpu-device option and GPU_DEVICE environment variable support to examples
- **fixed** — Fix macOS dSYM path case mismatch in XCFramework build
- **added** — Add VAD::Context#segments_from_samples to Ruby bindings and allow Pathname support
- **added** — Add Whisper::Context::Params to Ruby bindings
- **fixed** — Fix token memory management in Ruby bindings
- **fixed** — Fix hardcoded /inference path in server default HTML page
- **removed** — Drop obsolete build-time configuration of backends from CMake
- **changed** — Update miniaudio library to 0.11.24
- **fixed** — Fix null-check in Ruby bindings
- **fixed** — Return proper HTTP status codes for error responses in server
- **changed** — Allow max_len parameter to be used for any output format in server
- **fixed** — Replace deprecated openvino-dev with openvino>=2023.3.0 for Python 3.12+ compatibility
- **fixed** — Handle EOF correctly in model download example of Go bindings
- **fixed** — Fix VAD time mapping timestamp drift caused by overlap samples

##### Overview

Maintenance release, latest ggml, some performance gains across the board.

##### What's Changed
* Fix: UTF-8 character cut off to two "�" in segment wrapping (max_len) by @lordofriver in https://github.com/ggml-org/whisper.cpp/pull/3592
* examples: add -g/--gpu-device option and GPU_DEVICE env support by @brauliobo in https://github.com/ggml-org/whisper.cpp/pull/3557
* sync : ggml by @ggerganov in https://github.com/ggml-org/whisper.cpp/pull/3636
* Fix macOS dSYM path case mismatch in XCFramework build by @friederbluemle in https://github.com/ggml-org/whisper.cpp/pull/3630
* ruby : add `VAD::Context#segments_from_samples`, allow Pathname, etc. by @KitaitiMakoto in https://github.com/ggml-org/whisper.cpp/pull/3633
* ruby : add `Whisper::Context::Params`, fix token memory management by @KitaitiMakoto in https://github.com/ggml-org/whisper.cpp/pull/3647
* sync : ggml by @ggerganov in https://github.com/ggml-org/whisper.cpp/pull/3652
* ci : try fix mirrors by @ggerganov in https://github.com/ggml-org/whisper.cpp/pull/3655
* server : fix hardcoded /inference path in default HTML page by @sidmohan0 in https://github.com/ggml-org/whisper.cpp/pull/3639
* cmake: Drop obsolete build-time configuration of backends by @ckastner in https://github.com/ggml-org/whisper.cpp/pull/3649
* chore: Update outdated GitHub Actions versions by @pgoslatara in https://github.com/ggml-org/whisper.cpp/pull/3646
* ci: add vulkan docker image by @rare-magma in https://github.com/ggml-org/whisper.cpp/pull/3644
* sync : ggml by @ggerganov in https://github.com/ggml-org/whisper.cpp/pull/3665
* readme : fix duplicate word typo in VAD section by @cluster2600 in https://github.com/ggml-org/whisper.cpp/pull/3670
* cli: update miniaudio library to 0.11.24 by @data-man in https://github.com/ggml-org/whisper.cpp/pull/3672
* sync : ggml by @ggerganov in https://github.com/ggml-org/whisper.cpp/pull/3684
* ruby : null-check by @KitaitiMakoto in https://github.com/ggml-org/whisper.cpp/pull/3689
* sync : ggml by @ggerganov in https://github.com/ggml-org/whisper.cpp/pull/3710
* server : return proper HTTP status codes for error responses by @dearlordylord in https://github.com/ggml-org/whisper.cpp/pull/3707
* server: allow max_len to be used for any output format by @gaelj in https://github.com/ggml-org/whisper.cpp/pull/3679
* fix: replace deprecated openvino-dev with openvino>=2023.3.0 for Python 3.12+ compat by @Aiudadadadf in https://github.com/ggml-org/whisper.cpp/pull/3678
* fix(go): handle EOF correctly in model download example of golang bidings by @Lumberj3ck in https://github.com/ggml-org/whisper.cpp/pull/3671
* fix: VAD time mapping timestamp drift caused by overlap samples by @lohopupa in https://github.com/ggml-org/whisper.cpp/pull/3711
* sync : ggml by @ggerganov in https://github.com/ggml-org/whisper.cpp/pull/3713

##### New Contributors
* @lordofriver made their first contribution in https://github.com/ggml-org/whisper.cpp/pull/3592
* @brauliobo made their first contribution in https://github.com/ggml-org/whisper.cpp/pull/3557
* @friederbluemle made their first contribution in https://github.com/ggml-org/whisper.cpp/pull/3630
* @sidmohan0 made their first contribution in https://github.com/ggml-org/whisper.cpp/pull/3639
* @ckastner made their first contribution in https://github.com/ggml-org/whisper.cpp/pull/3649
* @pgoslatara made their first contribution in https://github.com/ggml-org/whisper.cpp/pull/3646
* @rare-magma made their first contribution in https://github.com/ggml-org/whisper.cpp/pull/3644
* @cluster2600 made their first contribution in https://github.com/ggml-org/whisper.cpp/pull/3670
* @dearlordylord made their first contribution in https://github.com/ggml-org/whisper.cpp/pull/3707
* @gaelj made their first contribution in https://github.com/ggml-org/whisper.cpp/pull/3679
* @Aiudadadadf made their first contribution in https://github.com/ggml-org/whisper.cpp/pull/3678
* @Lumberj3ck ma

_[Truncated at 4000 characters — full notes: https://github.com/ggml-org/whisper.cpp/releases/tag/v1.8.4]_

### v1.8.3

- Date: 2026-01-15
- Version: v1.8.3
- Original notes: https://github.com/ggml-org/whisper.cpp/releases/tag/v1.8.3
- Permalink: https://whatsnew.fyi/product/whisper-cpp/releases/v1.8.3

- **changed** — Server sets no_context to true
- **fixed** — WASM example broken for Hebrew
- **fixed** — Ruby tiny bug fix
- **changed** — 12x performance boost with integrated graphics
- **changed** — Ruby VAD separately from ASR
- **changed** — Silero VAD updated to v6.2.0
- **fixed** — Add missing cmath include to compile on macOS 11
- **added** — Add verified device of Ascend NPU
- **fixed** — Fix typo in vad-speech-segments command
- **changed** — Update VAD tests to use Silero V6.2.0
- **fixed** — Fix buffer overflow in sample reduction loop
- **changed** — Allow NextSegment() to be called across multiple Process() calls in the Go binding
- **added** — Enable VAD for Go bindings
- **added** — Server allows custom temp directory for ffmpeg
- **fixed** — Fix FreeBSD linker error: undefined reference to pthread_create
- **changed** — Ruby add Whisper::Token and fix model URI
- **fixed** — Ruby fix segmentation fault
- **fixed** — CMake fix executable example targets

##### Overview

Maintenance release, latest ggml, minor improvements in the tools/server/bindings.

##### What's Changed
* server : set no_context == true by @ggerganov in https://github.com/ggml-org/whisper.cpp/pull/3482
* WASM example broken for Hebrew by @Orel-A in https://github.com/ggml-org/whisper.cpp/pull/3487
* ruby : tiny bug fix by @KitaitiMakoto in https://github.com/ggml-org/whisper.cpp/pull/3490
* 12x Performance Boost with Integrated Graphics by @OrelSokolov in https://github.com/ggml-org/whisper.cpp/pull/3492
* ruby : VAD separately from ASR by @KitaitiMakoto in https://github.com/ggml-org/whisper.cpp/pull/3518
* vad : Silero VAD v6.2.0 by @KitaitiMakoto in https://github.com/ggml-org/whisper.cpp/pull/3524
* need to #include <cmath> to compile on macos 11 by @smilingpoplar in https://github.com/ggml-org/whisper.cpp/pull/3533
* Add verified device of Ascend NPU by @lrisguan in https://github.com/ggml-org/whisper.cpp/pull/3516
* examples : fix typo in vad-speech-segments command [no ci] by @danbev in https://github.com/ggml-org/whisper.cpp/pull/3535
* tests : update VAD tests to use Silero V6.2.0 by @danbev in https://github.com/ggml-org/whisper.cpp/pull/3534
* vad : fix buffer overflow in sample reduction loop by @josephsellers in https://github.com/ggml-org/whisper.cpp/pull/3558
* Allow NextSegment() to be called across multiple Process() calls in the Go binding by @joshmux in https://github.com/ggml-org/whisper.cpp/pull/3503
* Enable VAD for Go bindings by @joshmux in https://github.com/ggml-org/whisper.cpp/pull/3563
* server: allow custom temp directory for ffmpeg by @socram8888 in https://github.com/ggml-org/whisper.cpp/pull/3564
* Fix FreeBSD linker error: undefined reference to pthread_create by @rsmirnov90 in https://github.com/ggml-org/whisper.cpp/pull/3568
* ruby : add Whisper::Token, fix model URI by @KitaitiMakoto in https://github.com/ggml-org/whisper.cpp/pull/3575
* ruby : fix segmentation fault by @KitaitiMakoto in https://github.com/ggml-org/whisper.cpp/pull/3591
* cmake: fix executable example targets by @ink-splatters in https://github.com/ggml-org/whisper.cpp/pull/3600

##### New Contributors
* @Orel-A made their first contribution in https://github.com/ggml-org/whisper.cpp/pull/3487
* @OrelSokolov made their first contribution in https://github.com/ggml-org/whisper.cpp/pull/3492
* @smilingpoplar made their first contribution in https://github.com/ggml-org/whisper.cpp/pull/3533
* @lrisguan made their first contribution in https://github.com/ggml-org/whisper.cpp/pull/3516
* @josephsellers made their first contribution in https://github.com/ggml-org/whisper.cpp/pull/3558
* @joshmux made their first contribution in https://github.com/ggml-org/whisper.cpp/pull/3503
* @socram8888 made their first contribution in https://github.com/ggml-org/whisper.cpp/pull/3564
* @rsmirnov90 made their first contribution in https://github.com/ggml-org/whisper.cpp/pull/3568
* @ink-splatters made their first contribution in https://github.com/ggml-org/whisper.cpp/pull/3600

**Full Changelog**: https://github.com/ggml-org/whisper.cpp/compare/v1.8.2...v1.8.3

### v1.8.2

- Date: 2025-10-15
- Version: v1.8.2
- Original notes: https://github.com/ggml-org/whisper.cpp/releases/tag/v1.8.2
- Permalink: https://whatsnew.fyi/product/whisper-cpp/releases/v1.8.2

#### Overview

- Fix a bug in the ggml norm CPU scalar operator

##### What's Changed
* sync : ggml by @ggerganov in https://github.com/ggml-org/whisper.cpp/pull/3478


**Full Changelog**: https://github.com/ggml-org/whisper.cpp/compare/v1.8.1...v1.8.2

### v1.8.1

- Date: 2025-10-12
- Version: v1.8.1
- Original notes: https://github.com/ggml-org/whisper.cpp/releases/tag/v1.8.1
- Permalink: https://whatsnew.fyi/product/whisper-cpp/releases/v1.8.1

##### Overview

- Fix Vulkan builds
- Fix memory leaks when using VAD
- Support `--carry-initial-prompt`

##### What's Changed
* bindings-java : disable flash attention by default by @danbev in https://github.com/ggml-org/whisper.cpp/pull/3445
* ruby : Loose RegExp of a test to follow change of flash attension default by @KitaitiMakoto in https://github.com/ggml-org/whisper.cpp/pull/3448
* vad : fix memory leaks in VAD implementation by @danbev in https://github.com/ggml-org/whisper.cpp/pull/3453
* ruby : Bump Ruby bindings' version to 1.3.4 by @KitaitiMakoto in https://github.com/ggml-org/whisper.cpp/pull/3461
* Fix vad leaks by @silviucpp in https://github.com/ggml-org/whisper.cpp/pull/3463
* cli: Fix assignment for vad_min_silence_duration_ms by @alubbe in https://github.com/ggml-org/whisper.cpp/pull/3467
* Add support for --carry-initial-prompt by @alubbe in https://github.com/ggml-org/whisper.cpp/pull/3395
* Support using devices of type iGPU by @0cc4m in https://github.com/ggml-org/whisper.cpp/pull/3469
* sync : ggml by @ggerganov in https://github.com/ggml-org/whisper.cpp/pull/3470

##### New Contributors
* @silviucpp made their first contribution in https://github.com/ggml-org/whisper.cpp/pull/3463
* @0cc4m made their first contribution in https://github.com/ggml-org/whisper.cpp/pull/3469

**Full Changelog**: https://github.com/ggml-org/whisper.cpp/compare/v1.8.0...v1.8.1