ATR AI Prompt Suite to Translate AtR Blog Articles

Awakening to Reality · AI resources

ATR AI Prompt Suite

A compact gateway to the full AtR translation and Blogger-publishing prompt suite, plus Cosmic Transcriber for long-form audio transcription.

Open the full prompt suite Download the HTML translation pack 中文页面

Current managed suite: Batch93 — cross-language knowing-function, hidden-agent, predicate-decomposition, Prompt 6/9 execution-evidence, and render-fixture hardening.

How to use the prompt suite

1. Open the full prompt-suite page or download the relevant prompt pack.
2. Use a current thinking/reasoning-capable system such as ChatGPT, Claude, Google Gemini, or another comparable system.
3. For a complete Blogger translation, begin with the Universal Intro Prompt and provide the source HTML, target language, and required output mode.
4. For publication-quality work, run the relevant Prompt 6 / Prompt 9 review and Strict HTML QA rather than stopping after the first draft.

Cosmic Transcriber v1.0.26

Cosmic Transcriber is Soh’s reviewed Windows 10/11 app for long MP3 lectures, interviews, podcasts, Dharma talks, folders, and multi-part recordings. It supports resumable batch transcription, TXT/Markdown output, and two complementary OpenAI model modes.

Download the compiled Windows app

Choose the model by purpose

• gpt-transcribe (default): the newer high-accuracy general model. Use it as the controlling text when exact wording, specialist terminology, multilingual speech, and negations matter. It supports language hints, literal keywords, and recording context, but does not add speaker labels in the app’s current file workflow.
• gpt-4o-transcribe-diarize: the older specialised speaker-labelled model. It identifies speaker turns and can include timestamps, but Cosmic Transcriber does not send prompt/context or structured keyword hints in this mode. Speaker letters may reset between independently processed Parts.

Soh’s recommended two-pass method: transcribe the same recording once with gpt-transcribe for the most reliable wording and once with gpt-4o-transcribe-diarize for speaker structure. Upload both outputs to ChatGPT; tell it to keep the first transcript as the wording authority and use the second only for speaker labels, timestamps, and turn boundaries. Ask it to mark uncertain alignments instead of guessing.

I am providing two transcripts of the same recording. Treat the gpt-transcribe output as controlling for exact wording, names, technical terms, negations, repetitions, and sentence content. Use the gpt-4o-transcribe-diarize output primarily for speaker labels, timestamps, and turn boundaries. Do not invent speech or speaker identities. Mark uncertain alignment instead of guessing.

Get an OpenAI API key

1. Sign in to the OpenAI API key page and create a new secret key.
2. Set up API billing in the OpenAI Platform billing page. API usage is billed separately from a ChatGPT subscription.
3. Copy the key once and keep it private. Do not post it, place it in public files, or share it with other people.

Quick use

1. Download and extract the ZIP, then start Cosmic Transcriber normally rather than as administrator.
2. Enter the API key for the session, load it from OPENAI_API_KEY, or optionally save it for the current Windows user using Windows DPAPI.
3. Add MP3 files or folders, choose the model and output options, then start transcription. Compatible completed chunks can resume from checkpoints.

Windows-only, MP3-oriented, internet-dependent completed-file transcription. It is not a live microphone recorder or audio editor. Speaker-labelled output is available only in diarization mode. Current model availability and pricing can change; check OpenAI’s current API pricing.

Back to Awakening to Reality · This Blogger page is intentionally lightweight; the complete executable prompt bodies remain on the standalone prompt-suite page and in the downloadable packs.