AUDIO MODEL · NARI LABS
Dia 1.6B
Dia 1.6B is Nari Labs’ dialogue speech model. It turns a written transcript into spoken audio and supports speaker tags, with a separate workflow for conditioning the voice on a supplied audio reference.
What you can do
- Text to speech
- Audio editing
Available versions
- Dia 1.6B
- Dia 1.6B · Voice clone
Sources
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-139e607888e4d531f6dc678a13ee3efb","operation":"text-to-speech","sku":"selected-settings-v1","input":{"parameters":{"p0":"A glass flower in soft studio light"}}}'SDKs
npm install renderly-ai
pip install renderly-ai