mozilla/DeepSpeech

Health v2 · maintenance only

Flags: archived

Adoption not part of the score

26771 stars · 4079 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

DeepSpeech is an open-source, offline speech-to-text engine based on Baidu's Deep Speech research paper and implemented with TensorFlow. It can run in real time on devices from a Raspberry Pi 4 to GPU servers, with pre-trained models and tooling for training custom models.

Use cases

• transcribe audio to text offline on a Raspberry Pi
• run speech recognition on-device without cloud services
• convert voice recordings to text in real time
• train a custom speech-to-text model
• add voice input to an embedded device

When to choose

• you need fully offline, on-device speech recognition on low-power hardware
• you want to fine-tune or train your own speech model with TensorFlow
• you need a lightweight STT engine for embedded Linux devices

When to avoid

• you need an actively maintained project - DeepSpeech is officially discontinued
• you need state-of-the-art accuracy on modern hardware, where newer engines like Whisper or Coqui STT are better
• you need cloud-scale multilingual transcription

Facets

library · maturity abandoned

speech-recognition machine-learning deep-learning speech-processing machine-learning embedded-systems cross-platform embedded python cpp speech-to-text offline on-device tensorflow discontinued raspberry-pi linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="mozilla/DeepSpeech")