Zum Inhalt springen
AI.info

AI Tools

whisper.cpp

whisper.cpp: Preise, Fähigkeiten, Updates und Alternativen, von den Seiten des Anbieters gelesen.

Die Website von whisper.cpp

Auf Englisch

Key facts

Price
Free plan · paid plans from $4/user/mo Read on github.com
Free plan
Yes Read on github.com
Platforms
Web · macOS · Windows · Linux · iOS · Android · CLI · API Read on github.com
API
Yes
Open source
Yes · MIT Read on github.com
Latest version
v1.9.5 Read on github.com
Last update
7 Oct 2026 Read on github.com
Prices checked
19 Nov 2026 Read on github.com

whisper.cpp runs Whisper model inference on audio. It includes command-line and library interfaces, an HTTP server example, continuous microphone transcription, and WebAssembly examples. It supports CPU processing and optional hardware backends; model files are downloaded separately.

The project is for developers building local speech-to-text or audio-translation workflows. The repository says it performs inference only; it does not train models. No official product pricing page was found in the search, and no hosted service or paid plan was confirmed.

Category
Audio & Music
Read from the maker’s pages
2026-11-18

Company

ggml.ai

Features

  • Transcribe audio files with the whisper-cli command-line tool
  • Translate audio using Whisper models
  • Run continuous microphone transcription
  • Serve inference through the whisper-server example
  • Use CPU processing or supported GPU and accelerator backends
  • Build WebAssembly examples for browser use
  • MIT-licensed source code

Use cases

  • Transcribe recorded interviews on a local machine
  • Translate speech in audio files with a Whisper model
  • Add speech recognition to a C or C++ application
  • Stream microphone audio for continuous transcription
  • Build a browser-based transcription demo with WebAssembly

Pricing

Free plan · paid plans from $4/user/mo

Prices checked
2026-11-19

Free

free

  • Unlimited public/private repositories
  • Dependabot security and version updates
  • 2,000 CI/CD minutes/month
  • 500MB of Packages storage
  • Issues & Projects
  • Community support

Team

$4/user/mo

  • $ 4 USD per user / month
  • Access to GitHub Codespaces
  • Repository rules
  • Multiple reviewers in pull requests
  • Draft pull requests
  • Code owners
  • Required reviewers

Enterprise

$21/user/mo

  • $ 21 USD per user / month
  • GitHub Copilot access
  • Agent governance
  • Data residency
  • Enterprise Managed Users
  • User provisioning through SCIM
  • Enterprise Account to centrally manage multiple organizations

Capabilities

  • Speech to text — “Now build the whisper-cli example and transcribe an audio file like this:” source
  • API — “C-style API” source

Latest updates

  • Version 1.9.5

    Updated ggml to v0.26.0 and updated llama.cpp for talk-llama.

  • Version 1.9.4
  • Version b5127

    Windows arm64 CUDA builds use a preview CUDA Toolkit for Windows on Arm and are experimental.

  • Version 1.9.3
  • Version 1.9.2

    Added Parakeet to the XCFramework build, improved Android example inference performance, and updated UTF-8 voice lengths and VAD timestamps.

Where it works

Web · macOS · Windows · Linux · iOS · Android · CLI · API

Alternatives to whisper.cpp

  • Faster-Whisper

    A Python library for running Whisper speech-to-text models with CTranslate2 on CPU or GPU.

  • OpenAI Whisper

    OpenAI Whisper is an open-source model and Python command-line tool for transcribing speech, translating speech into English, and identifying spoken languages.

  • Cleanvoice

    Cleanvoice edits and enhances recorded audio and video, removing unwanted sounds and producing transcripts, summaries, and show notes.

  • Podsqueeze

    Podsqueeze turns podcast audio or video into transcripts, show notes, clips, social posts, and other promotional content.

  • Saaras

    Sarvam’s Saaras converts speech into text, translation, transliteration, or code-mixed output across Indian languages and English.

  • Deepgram

    Deepgram provides APIs for transcribing speech, generating speech, analyzing audio, and building voice agents.

More from ggml.ai

  • llama.cpp

    Run language and vision-language models on CPU or GPU with a C/C++ inference runtime and optional API server.

Questions about whisper.cpp

Is whisper.cpp free?

Yes. whisper.cpp has a free plan. Paid plans start at $4/user/mo. Prices checked on 19 Nov 2026.

How much does whisper.cpp cost?

The plans on the maker’s pricing page: Free (free), Team ($4/user/mo) and Enterprise ($21/user/mo). Prices checked on 19 Nov 2026.

Does whisper.cpp have an API?

Yes. The maker’s pages state that whisper.cpp has an API. Read on the maker’s pages on 18 Nov 2026.

Which platforms does whisper.cpp run on?

whisper.cpp runs on Web, macOS, Windows, Linux, iOS, Android, CLI and API, as its maker’s pages state. Read on the maker’s pages on 18 Nov 2026.

Is whisper.cpp open source?

Yes. The code of whisper.cpp is published at github.com/ggml-org/whisper.cpp under the MIT licence. Read on the maker’s pages on 18 Nov 2026.

Is whisper.cpp still available?

Yes, as of 18 Nov 2026: its maker’s pages were read that day and carried no notice that whisper.cpp has ended.

What changed recently in whisper.cpp?

The latest entry in its maker’s changelog: 7 Oct 2026, “Version 1.9.5”. Before it: 11 Sept 2026, “Version 1.9.4”. Changelog checked on 14 Nov 2026.

Sources

Official website