Speech synthesis in the REST API v3

To reproduce this example, you will need the jq utility to work with JSON files.

1. Create the request.json file with the following request parameters:

   {"text": "Hi! I'm Yandex Speech+Kit. I can turn any text into speech. Now y+ou can, too!", "hints": [{"voice": "marina"}, {"role": "friendly"}]}
   

   Where:

   • text: Text to synthesize
   • hints: List of synthesis parameters:
     • voice: Voice for synthesis
     • role: Role

2. Run the request in the terminal by specifying the IAM token and the ID of the folder you will use to work with SpeechKit:

   export FOLDER_ID=<folder_ID>
   export IAM_TOKEN=<IAM_token>
   
   curl \
     --header "Authorization: Bearer $IAM_TOKEN" \
     --header "x-folder-id: $FOLDER_ID" \
     --data @request.json https://tts.api.cloud.yandex.net:443/tts/v3/utteranceSynthesis | \
     jq -r  '.result.audioChunk.data' | \
     while read chunk; do base64 -d <<< "$chunk" >> audio.wav; done
   

   Where:

   • FOLDER_ID is the ID of the folder for which your account has the ai.speechkit-tts.user role or higher. If using a service account, you do not need to include the folder ID in the request.
   • IAM_TOKEN: IAM token of your Yandex account or federated account.

   The synthesized speech will be Base64 encoded and saved to a file named audio.wav.