Streaming

Overview

The streaming endpoint delivers audio chunks as they’re generated, so your application can start playback before the full audio is ready. This is ideal for long-form content and low-latency applications.

Usage

1
import subprocess
2
from speechify import Speechify
3
4
client = Speechify()
5
6
with client.tts.audio.stream(
7
    input="Your long-form text content here...",
8
    voice_id="george",
9
    audio_format="mp3",
10
) as stream:
11
    # Write chunks to file as they arrive
12
    with open("output.mp3", "wb") as f:
13
        for chunk in stream:
14
            f.write(chunk)

Supported audio formats

Use cases

Error handling

To handle mid-stream failures:

• Check the total bytes received against expected audio length
• Implement retry logic for the remaining text

Example projects

See our Examples Repository for complete browser and server-side streaming demos.