Registry › Compare › Qwen Audio Agent vs Speech To Speech

Qwen Audio Agent vs Speech To Speech

Qwen Audio Agent leads on trust: 86.3/100 (Grade A) against 63.2/100 (Grade C), a 23.1-point gap. Qwen Audio Agent leads on supply-chain integrity and provenance, and rests on broader evidence; Speech To Speech leads on transparency.

A Qwen Audio Agent 86.3

A realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents

QwenAudio/qwen-audio-agent · #75 overall · #2 Voice & Conversational · coverage B (3/5)

Choose Qwen Audio Agent if supply-chain integrity and provenance matter most.

+9.3Safety / Integrity: 98% of recent commits signed, against 35%
+7.2Identity / Provenance: package provenance attested, against none
+1.6Adoption
B vs CEvidence coverage: 3 of 5 independent signal types, against 2

C Speech To Speech 63.2

Build voice agents with open-source models

huggingface/speech-to-speech · #577 overall · #5 Voice & Conversational · coverage C (2/5)

Choose Speech To Speech if transparency matters most.

+0.9Transparency: OSSF Scorecard 6.6 against 5.5

Where they differ

19.3

Safety / IntegrityQwen Audio Agent +9.3

10.0

18.0

Identity / ProvenanceQwen Audio Agent +7.2

10.8

13.2

TransparencySpeech To Speech +0.9

14.1

19.8

MaintenanceSpeech To Speech +0.1

19.9

11.5

AdoptionQwen Audio Agent +1.6

9.9

+4.5

Runtime calibrationQwen Audio Agent +6.0

-1.5

Full evidence table

An independent, evidence-based trust comparison of Qwen Audio Agent and Speech To Speech, 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	Speech To Speechhuggingface/speech-to-speech
HVTrust score	86.3	63.2
Evidence grade	A	C
Coverage grade	B	C
Overall rank	#75	#577
Rank in Voice & Conversational	#2	#5
GitHub stars	2.9k	13.4k
Last updated	1d ago	1d ago
Build provenance	Yes	No
OSSF Scorecard	5.5 / 10	6.6 / 10
License	Apache-2.0	Apache-2.0
Downloads	259/wk	—
Trust dimensions (points earned)
Safety / integrity / 25	19.3	10.0
Identity & provenance / 18	18.0	10.8
Transparency / 17	13.2	14.1
Maintenance / 20	19.8	19.9
Adoption / 20	11.5	9.9
Runtime capability surface (full matrix)
MCP server	Implemented	—
External providers	—	2 — OpenAI, OpenRouter
Requires API keys	Yes	Yes
Plugin surface	—	—
Provenance drift	Match	—

Open in the live compare tool → Qwen Audio Agent profile Speech To Speech profile More Voice & Conversational →

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 →