LANGUAGE MODEL · COHERE

Cohere Transcribe

Cohere Transcribe converts recorded speech into text. It is a dedicated speech recognition model for transcription workflows; its supported languages and input settings are specified in the model documentation.

See price and create Compare with other models Use it through the API

What you can do

Speech to text

Sources

Model documentation

Pricing

Renderly shows the exact price for your selected settings before you confirm. Prices are in USD and credits; one credit has a balance value of $0.01.

Use it through the API

Request a price quote with this model’s ID. Quoting does not spend credits; review the amount, then submit the job with the quote ID.

cURL · price quote

# Set RENDERLY_API_URL and RENDERLY_API_KEY as shown in the API guide.
curl --fail-with-body "$RENDERLY_API_URL/quotes" \
  -H "Authorization: Bearer $RENDERLY_API_KEY" \
  -H "Content-Type: application/json" \
  --data '{"modelId":"model-f6a64075c61feb35a8de87b9fbeb0cb2","operation":"speech-to-text","sku":"selected-settings-v1","input":{"parameters":{"p0":"en","p1":"YOUR_UPLOADED_ASSET_ID","p2":true,"p3":256}}}'

SDKs

npm install renderly-ai
pip install renderly-ai

Full example in the API guide