Google AI Edge Gallery Adds On-Device ASR and TTS Capabilities
11/13/2026 — 11/13, 13:17·1 sources (all)·1 reports (all)
Key takeaways
- Google has announced that its AI Edge Gallery now supports on-device offline automatic speech recognition and text-to-speech capabilities. D…
Background & analysis
On November 13, 2026 at 12:10, Google Developers Blog announced that Google AI Edge Gallery now supports on-device, offline Automatic Speech Recognition (ASR) and Text-to-Speech (TTS) capabilities. The post describes the update as a way to build developer-friendly voice applications entirely on the device, without relying on cloud processing for the speech pipeline.
Developers can integrate the new functionality through ML Kit, MediaPipe Tasks, or LiteRT. ML Kit is presented as the option for performance-optimized Android work, while MediaPipe Tasks and LiteRT are meant for cross-platform integration of open-weight models. According to the announcement, this local pipeline pairs lightweight speech models with on-device small language models such as Gemini Nano and Gemma 4, enabling real-time streaming transcription and local speech synthesis. The framing is that voice is a natural way to interact with AI on phones and wearables, and that recent advances in compact speech architectures make it feasible to run the needed models directly on the device.
At this stage, the on-device ASR and TTS capabilities are available in Google AI Edge Gallery, and developers can start building voice applications around them. No further updates, expansions, or changes to the feature set have been announced yet, so the release currently stands as the latest word on what the tool offers.
AI-generated from 1 reports · updated 8 hours ago
- Heat index
- 78
- All sources
- 1
- All reports
- 1
- First seen
- 9 hours ago
Reports on this story headlines open the original
Google has announced that AI Edge Gallery now supports on-device, offline Automatic Speech Recognition (ASR) and Text-to-Speech (TTS). Developers can leverage ML Kit, MediaPipe Tasks, and LiteRT to combine compact speech models with on-device small language models like Gemini Nano and Gemma 4 for real-time offline voice apps.
Google Developers BlogFirst-partyAI score 68
Other stories people are talking about
- Heat index 2236Nvidia stock plunges after Jensen Huang resigns, with retail investors buying the dip35 sources
- Heat index 1463RisingGoogle Opens Gemini 4 Hydrogen to All Users as High-Speed Model21 sources
- Heat index 1429SurgeJensen Huang exits as NVIDIA CEO, leadership vacuum lingers16 sources
- Heat index 785SurgeAnthropic hires gas supply lead to power data center expansion after IPO10 sources
- Heat index 673SurgeMicrosoft races to fix global outage hitting Outlook, Teams and Copilot8 sources
How is heat calculated?About the methodHide
Heat counts how many independent sources covered a story in the last 48 hours: one source counts once no matter how many posts it published, decaying with a 24-hour half-life. What ranks first is what many people are talking about.
This page aggregates public feeds. Headlines and summaries are machine-organized and remain the property of the original authors; verify important facts at the source. If you believe a headline or summary infringes your rights, email the contact address in the footer with the page URL and basis of your claim, and we will remove or replace it after review.
- Surge
- Discussion rising fast
- New
- First report within 6 hours
- Rising
- Still gathering discussion