Pricing
Not listed
Official monthly price not confirmed
- API
- GitHub distribution and CPU deployment advertised. Not confirmed: standalone hosted Hush API, deployment contract or embedding license terms.
Hush by Weya AI
● Identity checkedNoise suppression for voice AI audio · Official-source review 2026-10-09
Hush is Weya AI’s speech-enhancement model for suppressing background noise and competing voices in calls. It is intended to clean the audio input supplied to a voice agent or speech-recognition system.
- Category
- Noise suppression for voice AI audio
- Free access
- Open-source model download advertised, but exact license and standalone charges were not confirmed. Hosted Weya credits are introductory, not an ongoing Hush free plan.
- API access
- GitHub distribution and CPU deployment advertised. Not confirmed: standalone hosted Hush API, deployment contract or embedding license terms.
Is Hush by Weya AI right for you?
A good fit for
Relevant to voice developers comparing recognition quality on authorized noisy samples before integrating an audio filter.
Before you choose
Vendor reports roughly 8 MB model size and 0.9 ms per 10 ms frame; latency, main-speaker isolation and benchmark ranking were not tested. Denoising can remove useful speech or distort recognition. Weya platform pricing of $0.12+/voice minute or $0.062+/chat session with $10 introductory credit applies to hosted agents, not a verified Hush-only rate. Two-week managed pilot terms require a quote. No model downloaded, call captured, audio processed or agent deployed.
Workflow and handoff
Confirm the model license, compare original and cleaned authorized recordings, and measure word errors and latency on the intended hardware.
Pricing and practical limits
Vendor reports roughly 8 MB model size and 0.9 ms per 10 ms frame; latency, main-speaker isolation and benchmark ranking were not tested. Denoising can remove useful speech or distort recognition. Weya platform pricing of $0.12+/voice minute or $0.062+/chat session with $10 introductory credit applies to hosted agents, not a verified Hush-only rate. Two-week managed pilot terms require a quote. No model downloaded, call captured, audio processed or agent deployed.
Review method
Official product evidence reviewed on 2026-10-09; product artwork inspected visually. No hands-on vendor application test was performed. Application performance, security claims and plan enforcement were not independently tested.
What it can do
Features & capabilities
Unknown is different from unavailable. Each fact carries its own evidence.
| Capability | Value | Evidence | Checked |
|---|---|---|---|
| Product workflow | Hush is Weya AI’s speech-enhancement model for suppressing background noise and competing voices in calls. It is intended to clean the audio input supplied to a voice agent or speech-recognition system. | Facts sourced | 2026-10-09 |
| Pricing and restrictions | Vendor reports roughly 8 MB model size and 0.9 ms per 10 ms frame; latency, main-speaker isolation and benchmark ranking were not tested. Denoising can remove useful speech or distort recognition. Weya platform pricing of $0.12+/voice minute or $0.062+/chat session with $10 introductory credit applies to hosted agents, not a verified Hush-only rate. Two-week managed pilot terms require a quote. No model downloaded, call captured, audio processed or agent deployed. | Facts sourced | 2026-10-09 |
Understand the total cost
Hush by Weya AI pricing & plans
Alternatives to Hush by Weya AI
View all ↗
AI-cousticsai-coustics provides real-time audio intelligence SDKs that clean speech, remove background voices, and score audio quality for voice-AI pipelines. Voice Focus and related models target sub-30ms enhancement for production voice agents, with minute-based SaaS plans and enterprise SLAs.
Explore tool
TTS.aiTTS.ai is a multi-model text-to-speech platform with 36+ models, 314+ voices, voice cloning, speech-to-text, music, and marketplace listings. The homepage offers free generation without an account while paid plans add commercial licenses, API access, and longer downloads.
Explore tool
NovaSynth by NoveumNovaSynth tests agents with synthetic users over SIP phone calls, LiveKit audio and chat. It generates personas and scenarios, records traces and scores behaviors such as interruptions and recovery.
Explore toolThe practical questions
Frequently asked questions
Was the application hands-on tested?
No. This listing is based on dated official-source evidence and a visual artwork check. Unconfirmed costs and restrictions are identified explicitly.
What is Hush by Weya AI used for?
Hush is Weya AI’s speech-enhancement model for suppressing background noise and competing voices in calls. It is intended to clean the audio input supplied to a voice agent or speech-recognition system.
Does Hush by Weya AI have a free plan?
Open-source model download advertised, but exact license and standalone charges were not confirmed. Hosted Weya credits are introductory, not an ongoing Hush free plan.. This record does not confirm an ongoing free plan.
How much does Hush by Weya AI cost?
A listed monthly price has not been confirmed. See the plan cards for entitlements, billing commitments and seat minimums.
Can I use Hush by Weya AI through an API?
GitHub distribution and CPU deployment advertised. Not confirmed: standalone hosted Hush API, deployment contract or embedding license terms.. API access and subscription access may have different terms; consult the linked sources.
What should I check before choosing it?
Vendor reports roughly 8 MB model size and 0.9 ms per 10 ms frame; latency, main-speaker isolation and benchmark ranking were not tested. Denoising can remove useful speech or distort recognition. Weya platform pricing of $0.12+/voice minute or $0.062+/chat session with $10 introductory credit applies to hosted agents, not a verified Hush-only rate. Two-week managed pilot terms require a quote. No model downloaded, call captured, audio processed or agent deployed.
Price history
No retained pricing changes yet. A current price alone does not establish a historical trend.
How this profile is supported
Official product information
Current official product source read individually; product artwork inspected visually.
Read original source ↗Pricing review
Official pricing and billing restrictions read individually.
Read original source ↗Facts apply to the named version and check date. Send a sourced correction if something changed.