AI runtimepackages/ai/audio-pipeline
audio-pipeline package
Audio processing chain — voice clone, denoise, transcribe, summarize. Streams through one async iterator per stage.
- Stability
- Stable
- Scope
- Global
- Boundary
- packages/ai/audio-pipeline
audio-pipeline
packages/ai/audio-pipelineAI runtime · tool registry · MCP boundary
Ready
Capability graph
ai/audio-pipelineaudio-pipeline
Tool policy
Stream UI
Output
Run ledger
- 1Inputpackages/ai/audio-pipeline/request
- 2Planmessage reducer -> model turn
- 3Tool policytool schema · auth scope · rate limit
- 4Stream UIevents -> UI state machine
- 5Output@nebutra/agents response envelope
p50 latency
51 ms
events/sec
380/s
providers
4
eval score
84
Usageaudio-pipeline.ts
typescriptaudio-pipeline.ts
1import { audioPipeline } from "@nebutra/audio-pipeline";
2
3const result = await audioPipeline.run({
4 tenantId: org.id,
5 // audio-pipeline is part of the AI runtime — composable with other AI primitives.
6 input: payload,
7});