Apixly · API pricing
CosyVoice3
CosyVoice3 · Audio. Requires one voice reference and its transcript; Text instructions can adjust speaking style.
Voice cloningStyle instructionsReference audioReference transcript requiredSpeed controlAsync tasks
Gateway price for CosyVoice3 ↓API integration · Audio
Choose the documented audio operation for this model: speech synthesis and transcription have different inputs and outputs. Check the model list, voices or file formats in the audio guide before starting.
- Request model ID
- CosyVoice3
- Public groups
- audio
Create an Apixly API key, bind a group that lists this exact model, and keep the key in a server-side environment variable. Public prices exclude personal discounts; check the selected group before sending a request.
Check model access first
Run this read-only catalog request to inspect the exact model entry visible to your API key. Confirm its group, then follow the operation guide and verify a completed output and actual usage.
curl --fail-with-body --max-time 30 'https://apixly.ai/v1/models' -H "Authorization: Bearer $APIXLY_API_KEY" | python3 -c 'import json, sys
models = json.load(sys.stdin).get("data", [])
wanted = "CosyVoice3"
match = next((item for item in models if item.get("id") == wanted), None)
if match is None: raise SystemExit("Model not listed for this key; check its bound groups")
print(json.dumps(match, ensure_ascii=False, indent=2))'Use the model-specific parameters in the linked guide. For asynchronous jobs, keep the returned task ID, poll that same task to a terminal state and verify the downloadable result. Reconcile a timed-out request before submitting another paid job.
Compare related models
Public quotes
Public prices
Providers
- Speech synthesis/ 10,000 characters
- $1.34
/ 10,000 characters
Channel: audio
Use this providerOfficial prices and discounts use the same billing unit and tier.
Each price shows its own billing unit. Input, output, cache and reference media are charged separately where listed.