--- title: "AudioNotes vs whishper" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/harry0703-audionotes-vs-pluja-whishper" tools: ["harry0703-audionotes", "pluja-whishper"] --- # AudioNotes vs whishper *GraphCanon updated Sep 20, 2026* ## Verdict Pick AudioNotes if audioNotes utilizes AI to transcribe audio and video into structured markdown notes, offering developers an efficient way to document media content; pick whishper if whishper is an open-source audio transcription and subtitling suite with a web UI that supports both GPU and CPU for local transcription. [AudioNotes](https://github.com/harry0703/AudioNotes) reports 2.5k GitHub stars, 369 forks, and 9 open issues, last pushed Aug 19, 2026. [whishper](https://whishper-docs.pages.dev/) has 3.1k stars, 179 forks, and 108 open issues, last pushed Jul 31, 2026. Figures are from public GitHub metadata via [AudioNotes's repository](https://github.com/harry0703/AudioNotes) and [whishper's repository](https://github.com/pluja/whishper). | | [AudioNotes](/tools/harry0703-audionotes.md) | [whishper](/tools/pluja-whishper.md) | | --- | --- | --- | | Tagline | Quickly extracts audio and video content into structured markdown notes | Open-source local audio transcription and subtitling suite with web UI | | Stars | 2,509 | 3,066 | | Forks | 369 | 179 | | Open issues | 9 | 108 | | Language | Python | Svelte | | Adopt for | AudioNotes utilizes AI to transcribe audio and video into structured markdown notes, offering developers an efficient way to document media content. | Whishper is an open-source audio transcription and subtitling suite with a web UI that supports both GPU and CPU for local transcription. | | Persona | - | - | | Runtime | - | - | | License | MIT | Whishper uses the AGPL-3.0 license, requiring users who modify and deploy the software in a network service to make their changes available under the same license. | | Categories | Developer Tools, Speech & Audio | Developer Tools, Speech & Audio | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [AudioNotes](/tools/harry0703-audionotes.md) | [whishper](/tools/pluja-whishper.md) | | --- | --- | --- | | Maintenance | Steady (60%) | Active (82%) | | Days since push | 31d | 29d | | Open issues (now) | 9 | 108 | | Stars delta | +250 (30d) | +18 (30d) | | Open issues delta | +1 (30d) | 0 (30d) | | Full report | [trust report](/tools/harry0703-audionotes/trust.md) | [trust report](/tools/pluja-whishper/trust.md) | ## Decision facts: AudioNotes - **Adopt for:** AudioNotes utilizes AI to transcribe audio and video into structured markdown notes, offering developers an efficient way to document media content. ## Decision facts: whishper - **Pricing:** freemium - Free, open-source solution that does not charge for usage or require payment plans. - **Requirements:** Min 4 GB RAM; Requires Docker; Supports both GPU and CPU for processing.; NVIDIA GPU is optional. - **Adopt for:** Whishper is an open-source audio transcription and subtitling suite with a web UI that supports both GPU and CPU for local transcription. - **License detail:** Whishper uses the AGPL-3.0 license, requiring users who modify and deploy the software in a network service to make their changes available under the same license. ## Choose when ### Choose AudioNotes if… - AudioNotes is primarily Python; whishper is Svelte. - License: AudioNotes is MIT, whishper is AGPL-3.0. - Tags unique to AudioNotes: ai, asr, funasr, ollama. - When seeking a tool that integrates with Python for transcription tasks ### Choose whishper if… - whishper is primarily Svelte; AudioNotes is Python. - License: whishper is AGPL-3.0, AudioNotes is MIT. - Pricing: Free, open-source solution that does not charge for usage or require payment plans.. - Requirements: Min 4 GB RAM; Requires Docker; Supports both GPU and CPU for processing.; NVIDIA GPU is optional.. - Tags unique to whishper: audio-to-text, golang, speech recognition, speech-to-text. - When you need to transcribe media files locally without sending data to external servers, ensuring privacy. ## When NOT to use AudioNotes - Avoid if you do not need the output specifically in markdown format - Not recommended if your environment cannot support at least 12GB of RAM dedicated to Docker Desktop ## When NOT to use whishper - When real-time transcription accuracy outweighs local processing needs, because while faster on CPU, it may not offer the same level of immediate precision as cloud-based solutions. - If your project is resource-constrained, especially in terms of development time and effort required for setup since Whishper involves a few manual steps to start using. - When direct audio input from web browsers is necessary because this feature is pending implementation. ## Common questions ### What is the difference between AudioNotes and whishper? AudioNotes: Quickly extracts audio and video content into structured markdown notes. whishper: Open-source local audio transcription and subtitling suite with web UI. See the comparison table for live GitHub stats and shared categories. ### When should I choose AudioNotes over whishper? Choose AudioNotes over whishper when AudioNotes is primarily Python; whishper is Svelte; License: AudioNotes is MIT, whishper is AGPL-3.0; Tags unique to AudioNotes: ai, asr, funasr, ollama; When seeking a tool that integrates with Python for transcription tasks. ### When should I choose whishper over AudioNotes? Choose whishper over AudioNotes when whishper is primarily Svelte; AudioNotes is Python; License: whishper is AGPL-3.0, AudioNotes is MIT; Pricing: Free, open-source solution that does not charge for usage or require payment plans.; Requirements: Min 4 GB RAM; Requires Docker; Supports both GPU and CPU for processing.; NVIDIA GPU is optional.; Tags unique to whishper: audio-to-text, golang, speech recognition, speech-to-text; When you need to transcribe media files locally without sending data to external servers, ensuring privacy. ### When should I avoid AudioNotes? Avoid if you do not need the output specifically in markdown format Not recommended if your environment cannot support at least 12GB of RAM dedicated to Docker Desktop ### When should I avoid whishper? When real-time transcription accuracy outweighs local processing needs, because while faster on CPU, it may not offer the same level of immediate precision as cloud-based solutions. If your project is resource-constrained, especially in terms of development time and effort required for setup since Whishper involves a few manual steps to start using. When direct audio input from web browsers is necessary because this feature is pending implementation. ### Is AudioNotes or whishper more popular on GitHub? whishper has more GitHub stars (3,066 vs 2,509). Stars measure visibility, not whether either tool fits your constraints. ### Are AudioNotes and whishper open source? Yes - both are open-source projects on GitHub (AudioNotes: MIT, whishper: AGPL-3.0). ### Where can I find alternatives to AudioNotes or whishper? GraphCanon lists graph-backed alternatives at [AudioNotes alternatives](/tools/harry0703-audionotes/alternatives) and [whishper alternatives](/tools/pluja-whishper/alternatives) ([AudioNotes markdown twin](/tools/harry0703-audionotes/alternatives.md), [whishper markdown twin](/tools/pluja-whishper/alternatives.md)), ranked by typed relationship edges rather than popularity votes. ### Is there a machine-readable version of this comparison? Yes. The markdown twin at [this comparison](/compare/harry0703-audionotes-vs-pluja-whishper.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, AudioNotes or whishper? AudioNotes: Steady. whishper: Active. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance. ### Where are the full trust reports for AudioNotes and whishper? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [AudioNotes trust report](/tools/harry0703-audionotes/trust); [whishper trust report](/tools/pluja-whishper/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=harry0703-audionotes`](/api/graphcanon/graph?tool=harry0703-audionotes) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_