Get Text-to-Speech Result
Retrieves the result of a specific Text-to-Speech run using the provided run_id
.
This endpoint is the final step in your text-to-speech journey, where you retrieve your completed audio file. Once your task has reached a SUCCESS
status and you’ve received a run_id
, you can use this endpoint to access your generated audio and incorporate it into your application.
How to Use this Endpoint
Retrieving your generated audio is straightforward - simply make a GET
request to this endpoint with the run_id
you received when your task completed. The system will respond by providing your audio in your preferred format.
Understanding Response Options
This endpoint offers flexibility in how you receive your audio content. You can specify your preference using the output_type
parameter:
Output Type | Description | Best For |
---|---|---|
raw_bytes | Direct streaming of audio data (default option) | Immediate playback or saving to local storage |
file_url | JSON response with a URL to download the audio file | When you need to share or store the audio URL |
Working with Raw Bytes
When using the default raw_bytes
output type, the endpoint streams the audio data directly to your application. This approach is ideal when you want to:
- Save the audio file to your local system
- Process the audio data immediately in your application
- Play the audio without storing it permanently
Working with File URLs
If you prefer to receive a URL pointing to your audio file instead of the raw data, specify output_type=file_url
. The response will be a JSON object containing a URL where the audio file can be accessed. This approach is beneficial when:
- You need to share the audio file with others
- Embed the audio in web content
- Handle the download process separately from retrieval
Examples
Saving Audio to a File
Here’s how to retrieve and save your generated audio using Python:
Getting a File URL
If you prefer to receive a URL to the audio file instead:
Next Steps
Now that you’ve successfully retrieved your generated audio, you can:
- Incorporate it into your applications or websites.
- Process it further with audio editing tools.
- Combine multiple audio segments into a cohesive narrative.
- Share it with your users through your platform.
With these capabilities, you have everything you need to build rich, accessible voice experiences into your applications.
Authorizations
The x-api-key
is a custom header required for authenticating requests to our API. Include this header in your request with the appropriate API key value to securely access our endpoints. You can find your API key(s) in the 'API' section of our studio website.
Path Parameters
The unique identifier for the run, which was generated during the creation process and returned upon task completion.
Query Parameters
The type of the Text-to-Speech output to return. Either streamable audio bytes or a URL to the generated file.
raw_bytes
, file_url
Response
The generated audio file bytes in FLAC format, representing the speech created from the Text-to-Speech task.