AssemblyAI Realtime / Streaming
AssemblyAI's WebSocket streaming endpoint for live captions and agents.
Drop your audio. Transcript in seconds. First transcript free, then $4 = 300 min
Best for live captioning, real-time voice agents, contact-center streaming use cases. Pricing: from $0.15/hr (Streaming).
What it is
AssemblyAI Streaming (v3 WebSocket) is the real-time variant of AssemblyAI's ASR, returning partial and final transcripts as audio is streamed in. Used for live captions and voice agents. Distinct from the 'assemblyai' batch entry already in this directory; pricing and features differ per their public pricing page. Best fit: live captioning, real-time voice agents, contact-center streaming use cases. Caveats: distinct from the 'assemblyai' batch entry already in the directory. Pricing as listed: from $0.15/hr (Streaming). Feature flags from vendor docs: word-level timestamps, streaming, HIPAA-eligible under BAA. Directory tags: commercial-api, streaming. Last vendor-page check: 2026-05-12.
Watch out for: Distinct from the 'assemblyai' batch entry already in the directory.
Install / use
wss://streaming.assemblyai.com/v3/ws
Features
| Speaker diarization | No |
| Word-level timestamps | Yes |
| Streaming / real-time | Yes |
| Languages supported | None |
| HIPAA eligible | Yes |
AssemblyAI Realtime / Streaming vs Whipscribe
| Feature | AssemblyAI Realtime / Streaming | Whipscribe |
|---|---|---|
| Category | Transcription APIs | Transcription APIs |
| Pricing | Not verified | $4–$24 one-time packs (credits never expire) · $2 single unlock · 60 min free on signup |
| Speaker diarization | Not verified | Yes |
| Word timestamps | Not verified | Yes |
| Streaming | Not verified | No |
| Languages | — | 99 |
| Platforms | API | Web, API, MCP |
Alternatives to AssemblyAI Realtime / Streaming
Whipscribe is a managed faster-whisper + whisperX service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.