Sign inGet started
falSpeech to speechComing soon

xai/grok-voice/realtime

xai/grok-voice/realtime is a speech to speech tool from fal that runs in the background and returns audio. Coming soon: listed with its price, not yet open to runs.

This tool is listed but not yet available to run.

Priced by usage

Pricing

$0.001079 per second. Measured from the input file. The final charge comes from usage.

Limits

Runs
In the background
Returns
audio
Longest queue wait
3600s
Run deadline
1800s
Largest inline input
1024 KB
Largest input file
500 MB
Largest output
4768 MB
Outputs per run
16

Input

FieldKindDefaultDescription
audio_url requiredURL or file—URL of the audio containing the user's speech. The Grok agent listens to it and replies with speech. Most common audio formats are supported; the audio is converted to 16-bit 24 kHz mono PCM before being sent to Grok. Maximum duration 10 minutes, maximum file size 50 MB.
prompttext—Optional system instructions describing the agent's persona and conversation context. Uses Grok's default persona when omitted.
voiceone of
carina, zagan, helix, orion, luna, iris, altair, zenith, perseus, helios, lux, kepler, rigel, cosmo, celeste, ursa, sirius, lumen, castor, naksh, atlas, aurora, liora, ara, eve, leo, rex, sal
—Built-in xAI voice for the agent's reply. Uses Grok's default voice when omitted.
toolsJSON{"x_search":{"enabled":false},"web_search":{"enabled":false},"mcp_servers":[]}Server-side tools available to the agent. Web, X, and remote MCP tools are supported; every tool is disabled by default. file_search/collections are unsupported by the typed configuration due to ZDR.

Same request in code

curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "fal",
    "model": "xai/grok-voice/realtime",
    "input": {
      "audio_url": "https://v3b.fal.media/files/b/0a8dd5a2/hS140ygvRuxn-eY_qPhlv_assets_test_input_service.wav"
    }
  }'