ReplicateSpeech to textComing soon

google/gemini-3-pro

google/gemini-3-pro is a speech to text tool from Replicate that runs in the background and returns structured JSON. 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

Up to $1.533691 per run at the default inputs. The final charge comes from usage.

Limits

Runs
In the background
Returns
json
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
prompt requiredtext—The text prompt to send to the model
audioURL or filenullInput audio to send with the prompt (max 1 audio file, up to 8.4 hours)
top_pnumber
0 to 1
0.95Nucleus sampling parameter - the model considers the results of the tokens with top_p probability mass
imageslist[]Input images to send with the prompt (max 10 images, each up to 7MB)
videoslist[]Input videos to send with the prompt (max 10 videos, each up to 45 minutes)
video_fpsnumber
0.1 to 60
nullFrame rate (frames per second) at which to sample input videos. Higher values give the model more frames to reason over (useful for fast-moving footage) but consume more tokens. Omit to use the default sampling rate (1 fps).
temperaturenumber
0 to 2
1Sampling temperature between 0 and 2
thinking_levelJSONnoneThinking level for reasoning (low or high). Replaces thinking_budget for Gemini 3 models.
max_output_tokensnumber (whole)
1 to 65535
65535Maximum number of tokens to generate
system_instructiontextnullSystem instruction to guide the model's behavior

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": "replicate",
    "model": "google/gemini-3-pro",
    "input": {
      "prompt": "<prompt>"
    }
  }'