1 回答
- 最新
- 投票最多
- 评论最多
0
Can you describe the approach you are using to generate the audio, including which Amazon Polly API operations you're using?
If you're using the SynthesizeSpeech
operation be aware that it only synthesizes the first 3,000 characters. For longer passages of text you'll want to use Amazon Polly's asynchronous synthesis functionality. Details on how to do this can be found in the "Creating Long Audio Files" section of the Amazon Polly documentation.
Since you mentioned being able to generate 2 minute audio files I'm guessing you may already using the asynchronous synthesis operations, so if you can provide more detail about your code we may be able to help you troubleshoot.
已回答 2 年前
相关内容
- AWS 官方已更新 1 年前
- AWS 官方已更新 2 年前
- AWS 官方已更新 6 个月前
- AWS 官方已更新 1 年前