OpenAI Services

DuRT supports three OpenAI-powered services: Whisper for speech recognition, GPT models for AI assistance, and OpenAI TTS for voice synthesis. All three share the same API key and are billed pay-as-you-go through your OpenAI account.

NOTE

DuRT uses a BYOK (Bring Your Own Key) model. Your API key is stored locally on your Mac and is never transmitted to DuRT servers.

---

Step 1 — Get an OpenAI API Key

1. Go to platform.openai.com and sign in (or create an account).
2. Click your profile icon in the top-right corner and select API keys.
3. Click Create new secret key, give it a name (e.g. DuRT), and click Create.
4. Copy the key immediately — it will not be shown again.
5. Make sure your account has a positive credit balance under Billing.

TIP

Set a monthly usage limit under Billing → Limits to avoid unexpected charges.

---

OpenAI Whisper — ASR Service

OpenAI's Whisper API provides high-accuracy, cloud-based speech recognition with broad language support.

Add Whisper in DuRT

1. Open DuRT and go to Settings → Services.
2. Click ＋ Add Service and choose OpenAI Whisper.
3. Paste your API key into the API Key field.
4. (Optional) Select a preferred Language to improve accuracy and reduce latency. Leave it on Auto for automatic detection.
5. Click Save.

TIP

If you primarily speak one language, setting it explicitly speeds up recognition and reduces cost.

---

OpenAI GPT — LLM Service

Use GPT models for summarization, translation, meeting notes, and AI-assisted text processing within DuRT.

Add an OpenAI LLM Service in DuRT

1. Open DuRT and go to Settings → Services.
2. Click ＋ Add Service and choose OpenAI.
3. Paste your API key into the API Key field.
4. Select a Model from the dropdown (see recommendations below).
5. Click Save.

Model Recommendations

Model	Best For
gpt-4o	Best overall quality — summarization, complex tasks
gpt-4o-mini	Fast and cost-efficient — everyday tasks, translation
gpt-4-turbo	Long-context documents (128 K token window)

TIP

gpt-4o-mini offers an excellent balance of quality and cost for most daily use cases.

---

OpenAI TTS — Text-to-Speech Service

OpenAI TTS converts AI-generated or transcribed text to natural-sounding speech directly within DuRT.

Add OpenAI TTS in DuRT

1. Open DuRT and go to Settings → Services.
2. Click ＋ Add Service and choose OpenAI TTS.
3. Paste your API key into the API Key field.
4. Select a Voice and a Model (see below).
5. Click Save.

Available Voices

Voice	Character
alloy	Neutral, versatile
echo	Clear, measured
fable	Expressive, warm
onyx	Deep, authoritative
nova	Energetic, friendly
shimmer	Soft, gentle

TTS Models

Model	Description
tts-1	Low latency, good for real-time playback
tts-1-hd	Higher quality audio, slightly slower

TIP

Use tts-1 for quick previews and tts-1-hd when audio quality matters.

---

Cost & Tips

• All three services are pay-as-you-go — you only pay for what you use.
• There are no subscription fees beyond your OpenAI account balance.
• Reduce Whisper cost: Set an explicit language instead of using Auto-detect.
• Reduce LLM cost: Choose gpt-4o-mini for everyday tasks; reserve gpt-4o for complex ones.
• Monitor usage: Check platform.openai.com/usage regularly.

NOTE

Pricing is subject to change. Always refer to OpenAI's official pricing page for the latest rates.