Embedding Gemma Transcribe
No liveness check has reached it yet; it is registered on GitHub and has been in the index since 13 Oct 2026. How this is checked
Embedding Gemma Transcribe is a free macOS application that converts audio into English transcripts entirely on Apple Silicon devices. It uses a reader trained on Google's EmbeddingGemma 2 model and adds punctuation and capitalization while processing recordings locally.
Inferred · not functionally tested
Overview
6 featuresPurpose: Transcribing long audio recordings quickly without uploading them to a cloud service.
Inferred · not functionally tested
Audience: Mac users who need fast private audio transcription
Inferred · not functionally tested
Functions: speech_to_text
Inferred · not functionally tested
Interfaces: API: unknown · MCP: unknown · CLI: unknown · Self-hosting: unknown
Recorded constraints: pricing: free · license: Apache-2.0 · platforms: DESKTOP, WEB · deployment: browser, macos
Constraint provenance is unknown; confirm requirements with the publisher.
Record sources: eg2.haku.sh · github.com. These links do not verify the individual claims.
Embedding Gemma Transcribe is a Speech to text project. Inferred · not functionally tested: It focuses on transcribing long audio recordings quickly without uploading them to a cloud service. Inferred · not functionally tested: Embedding Gemma Transcribe is a consumer product aimed at mac users who need fast private audio transcription. Basis unknown · not verified: It is available for free. Basis unknown · not verified: Embedding Gemma Transcribe is available on the web and macOS.
It is developed by Google, and it first shipped in 2025. The project is developed in the open on GitHub with 3k stars and 141 commits in the last 90 days. Inferred · not functionally tested: Key capabilities include on-device transcription, english transcription, and audio processing.
Summary written by a language model from the project’s public pages.
Tasks: Inferred · not functionally tested
- On-device transcription
- English transcription
- Audio processing
- Automatic punctuation
- Capitalization
- Apple Silicon support
Topics: Inferred · not functionally tested
Built with & integrations
- Claude Code
- commit 5453d83431e4 · since Sep 2026
- Vercel
- x-vercel-id header · x-vercel-cache header
Trust & compliance
Indexing history
1What PulseGate has recorded for this listing
- Indexed13 Oct · 11:28 UTCAn hour of audio transcribed in about 13s on MacBook Air seen via Hacker News firehose (Algolia)Source: Hacker News firehose (Algolia) · Open
Frequently asked questions about Embedding Gemma Transcribe
- What does Embedding Gemma Transcribe do?
- Inferred · not functionally tested: Embedding Gemma Transcribe focuses on transcribing long audio recordings quickly without uploading them to a cloud service. It is catalogued under Speech to text on PulseGate.
- Who is Embedding Gemma Transcribe for?
- Inferred · not functionally tested: Embedding Gemma Transcribe is a consumer product built for mac users who need fast private audio transcription.
- Does Embedding Gemma Transcribe have a free plan?
- Basis unknown · not verified: Yes — Embedding Gemma Transcribe is free to use.
- What platforms does Embedding Gemma Transcribe run on?
- Basis unknown · not verified: Embedding Gemma Transcribe runs on the web and macOS.
- Is Embedding Gemma Transcribe still active?
- The GitHub repository shows 141 commits in the last 90 days.
- What projects are similar to Embedding Gemma Transcribe?
- Similar projects tracked by PulseGate include Whisperly, Whisperly Dictation, and Weavly - Keyboard Dictation.WhisperlyWhisperly DictationWeavly - Keyboard Dictation
- Who develops Embedding Gemma Transcribe?
- Embedding Gemma Transcribe is developed by Google.
- How long has Embedding Gemma Transcribe been around?
- Embedding Gemma Transcribe first shipped in 2025.
Also in Speech to text
Same category — not a similarity match