Node pricing
Mixers
Section titled “Mixers”| Node | USD/min | Notes |
|---|---|---|
video_mixer | $0.002 | Flat rate, up to 16 inputs; billed on processed videoMillis (wall-clock time while compositing, not nominal canvas.fps) |
audio_mixer | $0.0005 | Flat rate while mixing |
Billed only while the mixer is processing frames.
Per-track audio processing
Section titled “Per-track audio processing”| Node | USD/active track-min | Notes |
|---|---|---|
audio_resample | $0.00005 | Billed from the sum of processed audio duration across all tracks |
audio_resample is n:n, so simultaneous tracks are billed independently.
For example, three tracks processed for 60 minutes produce 180 active
track-minutes. inputCount is not applied as a second multiplier.
Managed AI nodes
Section titled “Managed AI nodes”ASR, Translate, and Voice Agent use AVFlow-managed services. Their listed rates include the underlying AI service and AVFlow orchestration.
| USD/min | Notes |
|---|---|
| $0.012 | Per minute of VAD-selected audio sent to the recognition service (asrProcessedMillis); includes speech recognition and orchestration |
Silence removed before provider transmission is not billed. The processed duration includes the short preroll and hangover retained around each speech segment so words are not clipped.
Translate
Section titled “Translate”| USD/min | Notes |
|---|---|
| $0.04 | While the speech-translation provider session is connected; includes managed OpenAI or Gemini translation and orchestration |
Diagnostic input/output audio durations are reported separately, but billing
uses activeConnectionSeconds.
Voice agent
Section titled “Voice agent”| USD/min | Notes |
|---|---|
| $0.10 | While the voice-agent provider session is connected; includes the managed voice service and orchestration |