Create Model Transcription

Transcribe audio with heygen-asr-1. Accepts WAV or MP3 as inline base64 up to 16 MiB or an accessible uploaded audio asset ID up to 32 MiB. Raw URL inputs are rejected. Asset access and contents are checked on each retry; changed audio with the same Idempotency-Key returns 409. Requires a non-trial API key with assets:write. Audio must decode to at most 30 minutes. Requires Idempotency-Key: identical retries return the stored result; a different request with the same key or a pending request returns 409. Charges API credits for decoded audio duration, rounded up to the wallet's smallest unit; failed calls are refunded. Returns the transcript and charged usage synchronously.