AssemblyAI

AssemblyAI’s Universal-3-pro model produces accurate English transcription with native speaker labels. It is the same model Quendian Cloud uses under the hood; with BYOK you connect your own AssemblyAI account directly.

Role: Transcription only

Role	Model
Transcription	universal-3-pro

---

Steps

1. Create an API key

Go to assemblyai.com and sign up or sign in.

Navigate to Your account → API keys in the dashboard and copy your key.

Key format: long alphanumeric string (no fixed prefix)

Add billing if needed — see AssemblyAI’s pricing page for current rates.

2. Open Preferences in Quendian

Navigate to Quendian → Preferences → Transcription.

3. Pick the preset, choose a region, paste your key

Select AssemblyAI from the provider dropdown (listed under Transcribe + speakers).

Pick your Region — US (default, api.assemblyai.com) or EU (api.eu.assemblyai.com). Both regions produce equivalent transcription quality. The choice determines where your audio is processed; see AssemblyAI’s data-retention docs for the implications.

Paste your API key and click Save.

---

What Quendian sends

Each transcription request sends:

• Your audio in WAV format, 16 kHz mono
• Request flags: speaker_labels: true, language_code: "en", transcript_ttl_seconds: 3600

The transcript_ttl_seconds: 3600 flag tells AssemblyAI to delete the transcript from their servers 1 hour after it is created. Audio files are subject to AssemblyAI’s standard retention period (approximately 24 hours per their documentation).

---

What you get back

• Full transcript text with word-level timestamps (used for click-to-jump in the Quendian transcript view)
• Speaker labels (Speaker A, Speaker B, …) mapped to Quendian’s global speaker IDs across sessions

---

Monitor usage and pricing

For current rates, see AssemblyAI’s pricing page. Track your usage at app.assemblyai.com/billing.