AssemblyAI vs Pepys
AssemblyAI
assemblyai.com
Pepys
pepys.coSide by side
| Figure | AssemblyAI | Pepys |
|---|---|---|
| Price from | $0.15/mo | Free |
| Free plan | Yes | Yes |
| Free trial | — | — |
| Open source | — | — |
| Web | Yes | Yes |
| API | Yes | Yes |
| Self-hosted | Yes | — |
| Plans published | 13 | 2 |
| Spec score · Podcast Transcription Software | 8.8 (#5) | 8.2 (#11) |
| Integrations | Official integrations include LiveKit, Pipecat, OpenRouter, Zapier, Make, n8n, Postman, Recall.ai, Zoom RTMS, Telnyx, Twilio, Amazon Connect, Genesys Cloud, LangChain, Vercel AI SDK, Power Automate, Semantic Kernel, Cloudflare, Bubble, Pipedream, and Drupal. | Pepys integrates with Google Drive, OneDrive, Zoom, Telegram, Chrome, ChatGPT and Claude, and exposes a direct API and MCP server. |
| Security | AssemblyAI offers TLS 1.2+ encryption in transit, AES-256 encryption at rest, zero data retention, and an opt-out from model training. | Pepys states that data is encrypted in transit with HTTPS/TLS and encrypted at rest through its infrastructure providers. |
Plans
AssemblyAI
- Free creditsFree
- Pay as you go — Universal-2$0.15 a month
- Pay as you go — Universal-3.5 Pro$0.21 a month
- Pay as you go — Universal-Streaming$0.15 a month
- Pay as you go — Universal-3.5 Pro Realtime$0.45 a month
- Free tierFree
- Universal-2$0.15 a month
- Universal-Streaming$0.15 a month
- Universal-Streaming Multilingual$0.15 a month
- Universal-3.5 Pro$0.21 a month
In their own words
AssemblyAI
AssemblyAI provides Voice AI models and APIs for speech-to-text, speech understanding, and voice applications. Its Speech Understanding API can identify and diarize speakers, summarize speech, extract action items and key phrases, detect sentiment, entities, and topics, and handle formatting, language detection, translation, PII redaction, and content moderation. The platform lists support for 99 languages and translation into 86. It offers streaming and voice-agent latency below 300ms and states that it processes more than 800 million API calls per month. Use its managed cloud or self-host models in your own environment; the service also lists API access and integrations including Twilio, Zoom RTMS, Zapier, and LangChain. Security options include TLS 1.2+ in transit, AES-256 at rest, zero data retention, and opting out of model training. A free tier is available. Pay-as-you-go billing is based on usage, with monthly invoices and no minimum commitments. Universal-2 is listed at $0.15 per hour of audio; Universal-3.6 Pro Realtime is $0.45 per hour.
Pepys
Pepys converts uploaded audio, video, links, cloud recordings, and podcast feeds into searchable, timestamped transcripts. It transcribes in 99 or more languages with automatic language detection. Each transcript may include an AI summary, key moments or chapters, translation, and chat answers linked to timestamps. Supported inputs include MP3, WAV, M4A, MP4, and MOV, plus links from YouTube, TikTok, Instagram, Facebook, Spotify, Apple Podcasts, and podcast RSS. Exports cover TXT, Markdown, DOCX, PDF, SRT, VTT, and JSON, with timestamps retained in subtitle files. Integrations include Google Drive, OneDrive, Zoom, Telegram, Chrome, ChatGPT, and Claude; Pepys also offers a direct API and MCP server. API and integration use consume transcription credits without per-seat fees, subscriptions, or credit expiration. The Forever Free plan includes signup and demo minutes, while pay-as-you-go costs $0.85, paid once purchase. Source media is automatically purged after 30 days, while transcripts and exports remain.