--- title: "SenseVoice vs dia2" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/funaudiollm-sensevoice-vs-nari-labs-dia2" tools: ["funaudiollm-sensevoice", "nari-labs-dia2"] --- # SenseVoice vs dia2 *GraphCanon updated Sep 20, 2026* ## Verdict Pick SenseVoice when senseVoice is primarily C; dia2 is Python; pick dia2 when dia2 is primarily Python; SenseVoice is C. [SenseVoice](https://huggingface.co/spaces/FunAudioLLM/SenseVoice) reports 9.3k GitHub stars, 827 forks, and 7 open issues, last pushed Sep 10, 2026. [dia2](https://github.com/nari-labs/dia2) has 1.2k stars, 102 forks, and 5 open issues, last pushed Nov 29, 2025. Figures are from public GitHub metadata via [SenseVoice's repository](https://github.com/FunAudioLLM/SenseVoice) and [dia2's repository](https://github.com/nari-labs/dia2). | | [SenseVoice](/tools/funaudiollm-sensevoice.md) | [dia2](/tools/nari-labs-dia2.md) | | --- | --- | --- | | Tagline | Multilingual speech understanding toolkit with ASR, emotion recognition, and audio event detection. | TTS model capable of streaming conversational audio in real-time. | | Stars | 9,332 | 1,180 | | Forks | 827 | 102 | | Open issues | 7 | 5 | | Language | C | Python | | Adopt for | SenseVoice is ideal for applications needing fast multilingual ASR with emotion recognition and audio event detection in over 50 languages. | - | | Persona | - | - | | Runtime | - | - | | License | Other | Apache-2.0 | | Categories | Speech & Audio | Speech & Audio | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [SenseVoice](/tools/funaudiollm-sensevoice.md) | [dia2](/tools/nari-labs-dia2.md) | | --- | --- | --- | | Maintenance | Active (82%) | Slowing (36%) | | Days since push | 9d | 295d | | Open issues (now) | 7 | 5 | | Stars delta | +371 (30d) | +20 (30d) | | Open issues delta | +7 (30d) | 0 (30d) | | Full report | [trust report](/tools/funaudiollm-sensevoice/trust.md) | [trust report](/tools/nari-labs-dia2/trust.md) | ## Decision facts: SenseVoice - **Adopt for:** SenseVoice is ideal for applications needing fast multilingual ASR with emotion recognition and audio event detection in over 50 languages. ## Choose when ### Choose SenseVoice if… - SenseVoice is primarily C; dia2 is Python. - License: SenseVoice is Other, dia2 is Apache-2.0. - Tags unique to SenseVoice: asr, audio-analysis, audio-event-detection, cantonese. - SenseVoice ships Docker support for self-hosted deployment. - Projects requiring speed, with non-autoregressive models being up to 15 times faster than Whisper ### Choose dia2 if… - dia2 is primarily Python; SenseVoice is C. - License: dia2 is Apache-2.0, SenseVoice is Other. - Tags unique to dia2: open-weight, text-to-speech. - When you need real-time streaming capabilities for text-to-speech applications. ## When NOT to use SenseVoice - Applications needing Python-based implementation since SenseVoice relies on C and PyTorch for its framework - Scenarios demanding the lowest level of inference latency as it may have higher overhead compared to simpler models ## When NOT to use dia2 - For projects aimed at batch processing or non-realtime TTS applications where instantaneous audio output isn't required. - If you are looking for an open-source model that does not include specific proprietary components like the Kyutai Mimi codec. ## Common questions ### What is the difference between SenseVoice and dia2? SenseVoice: Multilingual speech understanding toolkit with ASR, emotion recognition, and audio event detection.. dia2: TTS model capable of streaming conversational audio in real-time.. See the comparison table for live GitHub stats and shared categories. ### When should I choose SenseVoice over dia2? Choose SenseVoice over dia2 when SenseVoice is primarily C; dia2 is Python; License: SenseVoice is Other, dia2 is Apache-2.0; Tags unique to SenseVoice: asr, audio-analysis, audio-event-detection, cantonese; SenseVoice ships Docker support for self-hosted deployment; Projects requiring speed, with non-autoregressive models being up to 15 times faster than Whisper. ### When should I choose dia2 over SenseVoice? Choose dia2 over SenseVoice when dia2 is primarily Python; SenseVoice is C; License: dia2 is Apache-2.0, SenseVoice is Other; Tags unique to dia2: open-weight, text-to-speech; When you need real-time streaming capabilities for text-to-speech applications. ### When should I avoid SenseVoice? Applications needing Python-based implementation since SenseVoice relies on C and PyTorch for its framework Scenarios demanding the lowest level of inference latency as it may have higher overhead compared to simpler models ### When should I avoid dia2? For projects aimed at batch processing or non-realtime TTS applications where instantaneous audio output isn't required. If you are looking for an open-source model that does not include specific proprietary components like the Kyutai Mimi codec. ### Is SenseVoice or dia2 more popular on GitHub? SenseVoice has more GitHub stars (9,332 vs 1,180). Stars measure visibility, not whether either tool fits your constraints. ### Are SenseVoice and dia2 open source? Yes - both are open-source projects on GitHub (SenseVoice: Other, dia2: Apache-2.0). ### Where can I find alternatives to SenseVoice or dia2? GraphCanon lists graph-backed alternatives at [SenseVoice alternatives](/tools/funaudiollm-sensevoice/alternatives) and [dia2 alternatives](/tools/nari-labs-dia2/alternatives) ([SenseVoice markdown twin](/tools/funaudiollm-sensevoice/alternatives.md), [dia2 markdown twin](/tools/nari-labs-dia2/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-sensevoice-vs-nari-labs-dia2.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, SenseVoice or dia2? SenseVoice: Active. dia2: Slowing. 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 SenseVoice and dia2? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [SenseVoice trust report](/tools/funaudiollm-sensevoice/trust); [dia2 trust report](/tools/nari-labs-dia2/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=funaudiollm-sensevoice`](/api/graphcanon/graph?tool=funaudiollm-sensevoice) - 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/_