CLUSTER TEXT-AUDIO-CONVERTS-2 · 15 ENTRIES · EARLIEST ENTRY 2025-02-03
On-device offline speech engines
This cluster comprises on-device, offline speech engines and applications for text-to-speech and speech-to-text, often supporting multiple languages and privacy-focused features. The dated entries before the index start are sparse and intermittent, appearing in 2021, 2023, 2025, and 2026, with the highest monthly count of two in July 2026. The traction leaders, Marmalade TTS, SIH-21673, and Supertonic TTS, each have 0 stars, indicating minimal activity.
Entry timeline
ENTRY TIMELINE
Each bar is the month a member carries, which is a creation date where the source published one and a crawl date otherwise. Nothing in the index was found before 11 August 2026, and coverage broadened sharply on 14–15 August, so a bar from then on reports how much we found that month, not how much was built; an earlier bar reports how far back a member's own source dated it — not how long we have been watching.
Members by activity
Activity signals, not revenue.
Build origin · 1 ai-built · 2 hand-coded · 12 unlabelled
Operator · 5 hobby · 1 indie · 9 open source
Two labels per entry, never collapsed into one: how it was built, and who stands behind it. Counted over the 15 listed below. Unlabelled means nothing has decided yet — not that the answer is small.
- 01kokoro-pi0★26 dayslivehand-codedhobbyOn-device text-to-speech server for Raspberry Pi that converts text to speech and connects to home assistant platforms.
- 02ebook2tts-local0★1 mo—hobbyOffline Android text-to-speech engine that enables e-book apps to read novels aloud with multiple character voices and no API key.
- 03Marmalade TTS0★8 daysliveopen sourceOn-device text-to-speech engine that gives the whole phone natural voices, per-app routing, and works offline.
- 04SIH-216730★27 days—hobbyAndroid app that enables offline multilingual voice communication over local Wi-Fi using on-device speech recognition and text-to-speech.
- 05commute-cast0★16 days—hobbyTool that turns articles, notes, and chat sessions into a private offline podcast for commutes, using on-device text-to-speech.
- 06BiVoice0★26 daysliveindieScreen reader speech engine for iPhone that gives each language its own voice and switches between them within a sentence.
- 07agentics-astt0★1 moliveopen sourceOn-device speech engine component that performs speech recognition and transcription within an AI ecosystem.
- 08SherpaTTS0★2 moliveopen sourceOffline text-to-speech engine for mobile devices that converts written text into spoken audio using downloaded voice models for accessibility and reading.
- 09agentics-astt-v20★3 moliveopen sourceOn-device speech engine that provides speech-to-text capabilities as an encrypted component launched at runtime.
- 10Supertonic TTS0★2 moliveopen sourceOn-device text-to-speech engine that converts written text to spoken audio offline, supporting multiple languages, voices, and custom pronunciation rules.
- 11Wyoming Android TTS0★1 yrabandonedliveopen sourceAndroid app that exposes device text-to-speech engines to Home Assistant via Wyoming protocol.
- 12eSpeak0★1 yrabandonedliveopen sourceOpen-source text-to-speech engine that converts written text into spoken audio in over a hundred languages, usable as a system-wide voice service.
- 13Parolu0★7 mostaleliveopen sourceOffline text-to-speech application that converts written text into spoken audio using multiple language voices without sending data to third parties.
- 14home-agent0★1 yrabandoned—ai-builthobbyLocal overlay application that performs real-time speech-to-text, optical character recognition, and translation using on-device language models.
- 15ChineseTtsTflite0★3 yrabandonedlivehand-codedopen sourceText-to-speech app that converts Chinese text into spoken audio completely offline.
Ranked by traction, highest first, and paged 20 at a time — this is a window on the cluster, never the whole of it. Ties are broken by a stable id so a product cannot appear on two pages or fall between them. Browse every cluster.