Skip to content
Prompt

hailo-apps — Cursor Rules

by hailo-ai

AI Summary

Build voice apps for all Hailo accelerators: Whisper STT on Hailo-8/8L/10H + optional Piper TTS on CPU. Create the app directory: Create with and wrapper.

Install

Copy this and paste it into Claude Code, Cursor, or any AI assistant:

I want to add the "hailo-apps — Cursor Rules" prompt rules to my project.
Repository: https://github.com/hailo-ai/hailo-apps

Please read the repo to find the rules/prompt file, then:
1. Download it to the correct location (.cursorrules, .windsurfrules, .github/prompts/, or project root — based on the file type)
2. If there's an existing rules file, merge the new rules in rather than overwriting
3. Confirm what was added

Description

Build voice apps for **all Hailo accelerators**: Whisper STT on Hailo-8/8L/10H + optional Piper TTS on CPU.

Skill: Build Voice Application

Build voice apps for all Hailo accelerators: Whisper STT on Hailo-8/8L/10H + optional Piper TTS on CPU.

When This Skill Is Loaded

• User wants speech input or speech output in a Hailo app • User mentions: voice, speech, Whisper, TTS, microphone, STT, speak, listen • User wants to add voice to an existing LLM or VLM app • User wants speech recognition on Hailo-8 or Hailo-8L

Hardware Compatibility

| Feature | Hailo-8/8L | Hailo-10H | |---|---|---| | STT (Whisper) | ✓ via InferModel (encoder+decoder HEFs) | ✓ via Speech2Text (genai API) | | LLM on device | ✘ | ✓ via hailo_platform.genai.LLM | | VLM on device | ✘ | ✓ via Backend (VLM chat) | | TTS (Piper) | ✓ CPU | ✓ CPU | | Full voice assistant | STT + CPU LLM + TTS | STT + on-device LLM + TTS |

Reference Implementations

Study these: • hailo_apps/python/gen_ai_apps/voice_assistant/ — Full voice + LLM assistant (Hailo-10H) • hailo_apps/python/gen_ai_apps/simple_whisper_chat/ — Simple STT example (Hailo-10H) • hailo_apps/python/standalone_apps/speech_recognition/ — STT for all Hailo devices (8/8L/10H) using InferModel API: • speech_recognition.py — Main app: mic recording, audio preprocessing, transcription loop • whisper_pipeline.py — WhisperPipeline class: encoder+decoder inference via InferModel • audio_utils.py — Audio recording, mel spectrogram, file I/O • postprocessing.py — Repetition penalty and token decoding • hailo_apps/python/gen_ai_apps/gen_ai_utils/voice_processing/ — Voice utilities (Hailo-10H): • speech_to_text.py — SpeechToTextProcessor (Whisper via genai API) • text_to_speech.py — TextToSpeechProcessor (Piper on CPU) • audio_recorder.py — AudioRecorder (microphone capture) • vad.py — Voice Activity Detection • interaction.py — VoiceInteractionManager (high-level orchestrator)

Discussion

0/2000
Loading comments...

Health Signals

MaintenanceCommitted 2mo ago
Active
Adoption100+ stars on GitHub
425 ★ · Growing
DocsREADME + description
Well-documented

GitHub Signals

Stars425
Forks145
Issues32
Updated2mo ago
View on GitHub
MIT License

My Fox Den

Community Rating

Sign in to rate this booster

Works With

Any AI assistant that accepts custom rules or system prompts

Claude
ChatGPT
Cursor
Windsurf
Copilot
+ more