Qwen Audio Agent vs TEN Framework
Qwen Audio Agent leads on trust: 87.1/100 (Grade A) against 58.6/100 (Grade C), a 28.5-point gap. Qwen Audio Agent leads on supply-chain integrity and provenance, and rests on broader evidence.
A realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents
Choose Qwen Audio Agent if supply-chain integrity and provenance matter most.
- +10.2Safety / Integrity: OSSF Scorecard 6.6 against 4.0
- +7.2Identity / Provenance: package provenance attested, against none
- +2.4Adoption
- +2.2Transparency: OSSF Scorecard 6.6 against 4.0
Open-source framework for conversational voice AI agents
TEN Framework doesn't lead on any scored dimension in this pair.
Where they differ
An independent, evidence-based trust comparison of Qwen Audio Agent and TEN Framework, two Voice & Conversational projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.
Full evidence
| Signal | Qwen Audio AgentQwenAudio/qwen-audio-agent | TEN FrameworkTEN-framework/ten-framework |
|---|---|---|
| HVTrust score | 87.1 | 58.6 |
| Evidence grade | A | C |
| Coverage grade | B | C |
| Overall rank | #74 | #758 |
| Rank in Voice & Conversational | #3 | #8 |
| GitHub stars | 3.2k | 11.2k |
| Last updated | 1d ago | today |
| Build provenance | Yes | No |
| OSSF Scorecard | 6.6 / 10 | 4.0 / 10 |
| License | Apache-2.0 | NOASSERTION |
| Downloads | 536/wk | — |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 20.2 | 10.0 |
| Identity & provenance / 18 | 18.0 | 10.8 |
| Transparency / 17 | 14.1 | 11.9 |
| Maintenance / 20 | 18.6 | 17.8 |
| Adoption / 20 | 12.1 | 9.7 |
| Runtime capability surface (full matrix) | ||
| MCP server | Implemented | — |
| External providers | — | 1 — OpenAI |
| Requires API keys | Yes | Yes |
| Plugin surface | — | extensions |
| Provenance drift | Match | — |
How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption, scaled by an evidence-confidence factor. Grade bands: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Signals refresh daily. Full methodology v4.4 →