Open-source project
Free
MIT code; inference infrastructure costs excluded
- Documented scope
- Web/iOS clients and Python fingerspelling inference
ASL fingerspelling recognition project · Official-source review 2026-10-09
Hand Wave is an open-source fingerspelling recognition project with web and iOS clients backed by a Python inference service. Its official repository describes recognizing hand signs and turning fingerspelling into speech, including smart-glasses experiments.
For developers researching handshape/fingerspelling recognition and willing to inspect setup and recognition limitations.
Fingerspelling recognition is not full sign-language interpretation. Setup needs Node22+, Python3.11/3.12, pnpm, Git LFS and a Modal backend account. Website offers camera and screen-share controls; recognition accuracy, dialect coverage and accessibility suitability were not tested. Mobile release uses TestFlight; smart-glasses capability is a repository description, not a verified supported-device guarantee. Visual streams may go to the inference backend; inspect privacy and retention before enabling. No camera, screen recording, inference, software installation or hardware test performed.
Review inference data flow and deployment setup, then evaluate recognition on representative signed input before any accessibility reliance.
Fingerspelling recognition is not full sign-language interpretation. Setup needs Node22+, Python3.11/3.12, pnpm, Git LFS and a Modal backend account. Website offers camera and screen-share controls; recognition accuracy, dialect coverage and accessibility suitability were not tested. Mobile release uses TestFlight; smart-glasses capability is a repository description, not a verified supported-device guarantee. Visual streams may go to the inference backend; inspect privacy and retention before enabling. No camera, screen recording, inference, software installation or hardware test performed.
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
Unknown is different from unavailable. Each fact carries its own evidence.
| Capability | Value | Evidence | Checked |
|---|---|---|---|
| Product workflow | Hand Wave is an open-source fingerspelling recognition project with web and iOS clients backed by a Python inference service. Its official repository describes recognizing hand signs and turning fingerspelling into speech, including smart-glasses experiments. | Facts sourced | 2026-10-09 |
| Pricing and restrictions | Fingerspelling recognition is not full sign-language interpretation. Setup needs Node22+, Python3.11/3.12, pnpm, Git LFS and a Modal backend account. Website offers camera and screen-share controls; recognition accuracy, dialect coverage and accessibility suitability were not tested. Mobile release uses TestFlight; smart-glasses capability is a repository description, not a verified supported-device guarantee. Visual streams may go to the inference backend; inspect privacy and retention before enabling. No camera, screen recording, inference, software installation or hardware test performed. | Facts sourced | 2026-10-09 |
Understand the total cost
Open-source project
Free
MIT code; inference infrastructure costs excluded
TTS.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 toolLM Studio is a desktop app for running local LLMs with the Bionic agent for work, code, and voice transcription. It combines on-device inference via llama.cpp and MLX with optional US-hosted cloud models under zero-data-retention policies.
Explore toolSayscroll uses speech recognition to keep a teleprompter aligned with spoken words. It supports mixed-language scripts, manual section jumps, display mirroring and browser video recording with device downloads.
Explore toolThe practical questions
No. This listing is based on dated official-source evidence and a visual artwork check. Unconfirmed costs and restrictions are identified explicitly.
Hand Wave is an open-source fingerspelling recognition project with web and iOS clients backed by a Python inference service. Its official repository describes recognizing hand signs and turning fingerspelling into speech, including smart-glasses experiments.
MIT source code available for ongoing self-use. Hosted backend compute, mobile distribution and hardware costs unconfirmed and separate.. This record lists ongoing free access; check the plan limits before starting.
No paid monthly price is listed; this record treats the product as free to start. See the plan cards for entitlements, billing commitments and seat minimums.
Python inference backend and client contract documented in the repository; stable public hosted API and quotas not confirmed.. API access and subscription access may have different terms; consult the linked sources.
Fingerspelling recognition is not full sign-language interpretation. Setup needs Node22+, Python3.11/3.12, pnpm, Git LFS and a Modal backend account. Website offers camera and screen-share controls; recognition accuracy, dialect coverage and accessibility suitability were not tested. Mobile release uses TestFlight; smart-glasses capability is a repository description, not a verified supported-device guarantee. Visual streams may go to the inference backend; inspect privacy and retention before enabling. No camera, screen recording, inference, software installation or hardware test performed.
No retained pricing changes yet. A current price alone does not establish a historical trend.
Current official product source read individually; product artwork inspected visually.
Read original source ↗Official product page reviewed for disclosed costs; unverified prices and allowances are identified in the listing.
Read original source ↗Facts apply to the named version and check date. Send a sourced correction if something changed.