Text to Speech (Stream)

POST

https://api.async.ai/text_to_speech/streaming

Generates speech using provided text and voice of your choice and returns audio in a stream.

Request Example

Shell

JavaScript

Java

Swift

curl --location --request POST 'https://api.async.ai/text_to_speech/streaming' \
--header 'x-api-key: <api-key>' \
--header 'version: v1' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model_id": "asyncflow_v2.0",
    "transcript": "Welcome to Async",
    "voice": {
        "mode": "id",
        "id": "e0f39dc4-f691-4e78-bba5-5c636692cc04"
    },
    "output_format": {
        "container": "raw",
        "encoding": "pcm_f32le",
        "sample_rate": 44100
    }
}'

Response Example

200 - Success

This endpoint returns an octet stream of the audio.

Request

Header Params

Body Params application/json

Examples

Responses

🟢200Success

application/octet-stream

If quota is exceeded during the stream the following bytes would be received: b"--ERROR:QUOTA_EXCEEDED--"

Body

🟠429TOO_MANY_CONCURRENT_REQUESTS

🟠429RATE_LIMIT_EXCEEDED

🟠429USAGE_LIMIT_EXCEEDED

🟠401INVALID_API_KEY

🟠404VOICE_NOT_FOUND

🟠404VERSION_NOT_FOUND

🟠400INVALID_LANGUAGE

🟠400FORMAT_NOT_RECOGNIZED

🔴500Server Error

Modified at 2025-07-16 06:29:12

Text to Speech with Word Timestamps

Clone Voice