--- title: "Fun-ASR vs murmure" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/funaudiollm-fun-asr-vs-kieirra-murmure" tools: ["funaudiollm-fun-asr", "kieirra-murmure"] --- # Fun-ASR vs murmure *GraphCanon updated Jul 31, 2026* ## Verdict Pick Fun-ASR if fun-ASR is a real-time speech recognition tool supporting 31 languages with capabilities for handling dialects, accents, and speaker diarization; pick murmure if murmure provides local and cross-platform speech-to-text service enhanced by LLM post-processing. [Fun-ASR](https://huggingface.co/spaces/FunAudioLLM/Fun-ASR-Nano) reports 1.4k GitHub stars, 141 forks, and 0 open issues, last pushed Jul 24, 2026. [murmure](https://www.murmure.app) has 979 stars, 88 forks, and 12 open issues, last pushed Jul 30, 2026. Figures are from public GitHub metadata via [Fun-ASR's repository](https://github.com/FunAudioLLM/Fun-ASR) and [murmure's repository](https://github.com/Kieirra/murmure). | | [Fun-ASR](/tools/funaudiollm-fun-asr.md) | [murmure](/tools/kieirra-murmure.md) | | --- | --- | --- | | Tagline | Fun-ASR-Nano LLM-ASR model supports 31 languages for real-time speech recognition tasks | Local, private Speech-to-Text with LLM Post-processing | | Stars | 1,449 | 979 | | Forks | 141 | 88 | | Open issues | 0 | 12 | | Language | C | TypeScript | | Adopt for | Fun-ASR is a real-time speech recognition tool supporting 31 languages with capabilities for handling dialects, accents, and speaker diarization. | Murmure provides local and cross-platform speech-to-text service enhanced by LLM post-processing. | | Persona | - | - | | Runtime | - | - | | License | Apache-2.0 | AGPL-3.0 | | Categories | LLM Frameworks, Speech & Audio | LLM Frameworks, Speech & Audio | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [Fun-ASR](/tools/funaudiollm-fun-asr.md) | [murmure](/tools/kieirra-murmure.md) | | --- | --- | --- | | Days since push | 6d | 0d | | Open issues (now) | 0 | 12 | | Owner type | Organization | User | | Full report | [trust report](/tools/funaudiollm-fun-asr/trust.md) | [trust report](/tools/kieirra-murmure/trust.md) | ## Decision facts: Fun-ASR - **Pricing:** freemium - Open source under Apache License 2.0 allows free use with attribution and adherence to the license terms. - **Requirements:** Installation requires Python packages `funasr` version >=1.3.3, and `vllm` version >=0.12.0. - **Adopt for:** Fun-ASR is a real-time speech recognition tool supporting 31 languages with capabilities for handling dialects, accents, and speaker diarization. - **License detail:** Apache-2.0 ## Decision facts: murmure - **Adopt for:** Murmure provides local and cross-platform speech-to-text service enhanced by LLM post-processing. ## Choose when ### Choose Fun-ASR if… - Fun-ASR is primarily C; murmure is TypeScript. - License: Fun-ASR is Apache-2.0, murmure is AGPL-3.0. - Pricing: Open source under Apache License 2.0 allows free use with attribution and adherence to the license terms.. - Requirements: Installation requires Python packages `funasr` version >=1.3.3, and `vllm` version >=0.12.0.. - Tags unique to Fun-ASR: audio-language-model, multilingual-asr, real-time-asr, speaker-diarization. - When you need support for 31 different languages including handling of various dialects and accents. ### Choose murmure if… - murmure is primarily TypeScript; Fun-ASR is C. - License: murmure is AGPL-3.0, Fun-ASR is Apache-2.0. - Tags unique to murmure: asr-model, privacy. - Use Murmure when you need to perform speech-to-text conversion on premises without relying on cloud services. ## When NOT to use Fun-ASR - Avoid if your project requires a specific programming language other than C as Fun-ASR is primarily developed in C. - If you do not require on-device processing, as this tool is designed for on-device inference which may limit scalability for cloud-based applications. ## When NOT to use murmure - Avoid using Murmure in scenarios where the flexibility of language model choices other than its designated LLM post-processing is required. - Do not use this tool when your project strictly requires real-time processing and cloud-scale resources for large audio data, asMurmele relies on local computation which may have limitations. ## Common questions ### What is the difference between Fun-ASR and murmure? Fun-ASR: Fun-ASR-Nano LLM-ASR model supports 31 languages for real-time speech recognition tasks. murmure: Local, private Speech-to-Text with LLM Post-processing. See the comparison table for live GitHub stats and shared categories. ### When should I choose Fun-ASR over murmure? Choose Fun-ASR over murmure when Fun-ASR is primarily C; murmure is TypeScript; License: Fun-ASR is Apache-2.0, murmure is AGPL-3.0; Pricing: Open source under Apache License 2.0 allows free use with attribution and adherence to the license terms.; Requirements: Installation requires Python packages `funasr` version >=1.3.3, and `vllm` version >=0.12.0.; Tags unique to Fun-ASR: audio-language-model, multilingual-asr, real-time-asr, speaker-diarization; When you need support for 31 different languages including handling of various dialects and accents. ### When should I choose murmure over Fun-ASR? Choose murmure over Fun-ASR when murmure is primarily TypeScript; Fun-ASR is C; License: murmure is AGPL-3.0, Fun-ASR is Apache-2.0; Tags unique to murmure: asr-model, privacy; Use Murmure when you need to perform speech-to-text conversion on premises without relying on cloud services. ### When should I avoid Fun-ASR? Avoid if your project requires a specific programming language other than C as Fun-ASR is primarily developed in C. If you do not require on-device processing, as this tool is designed for on-device inference which may limit scalability for cloud-based applications. ### When should I avoid murmure? Avoid using Murmure in scenarios where the flexibility of language model choices other than its designated LLM post-processing is required. Do not use this tool when your project strictly requires real-time processing and cloud-scale resources for large audio data, asMurmele relies on local computation which may have limitations. ### Is Fun-ASR or murmure more popular on GitHub? Fun-ASR has more GitHub stars (1,449 vs 979). Stars measure visibility, not whether either tool fits your constraints. ### Are Fun-ASR and murmure open source? Yes - both are open-source projects on GitHub (Fun-ASR: Apache-2.0, murmure: AGPL-3.0). ### Where can I find alternatives to Fun-ASR or murmure? GraphCanon lists graph-backed alternatives at [Fun-ASR alternatives](/tools/funaudiollm-fun-asr/alternatives) and [murmure alternatives](/tools/kieirra-murmure/alternatives) ([Fun-ASR markdown twin](/tools/funaudiollm-fun-asr/alternatives.md), [murmure markdown twin](/tools/kieirra-murmure/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/funaudiollm-fun-asr-vs-kieirra-murmure.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, Fun-ASR or murmure? Fun-ASR: Very active. murmure: Very 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 Fun-ASR and murmure? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [Fun-ASR trust report](/tools/funaudiollm-fun-asr/trust); [murmure trust report](/tools/kieirra-murmure/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=funaudiollm-fun-asr`](/api/graphcanon/graph?tool=funaudiollm-fun-asr) - 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/_