Zoom AI Services: Text-to-Speech API

Give your apps a
natural-sounding voice

Turn text into speech and start playback while audio is still being generated, all through a single API call. Text-to-Speech API streams high-fidelity audio so your AI agents, apps, and content can speak clearly and naturally. Choose from a curated selection of AI voices, with control over speed and volume.

Try demo See pricing

Capabilities

Speech delivered clearly

Streaming speech synthesis

Send text and receive audio streamed back in the same response. Playback can begin as soon as the first audio arrives, without needing to wait for the full file.

Natural AI voices to choose from

Pick from a selection of voices with distinct tones, from charming and friendly to professional and clear.

Speed and volume control

Fine-tune delivery with simple speed and volume settings in the request body, no markup required.

High-fidelity audio

Receive high-fidelity raw PCM audio, for real-time playback in apps, agents, and telephony flows.

One foundation

Add streamed speech where users need it

Start with natural-sounding streaming speech, then shape the AI voice experience for the people and systems that need it.

Conversational AI agents

Give AI voice agents streamed speech output designed for responsive interactions. Streaming audio lets replies start playing quickly, which can help conversations feel more fluid instead of scripted.

IVR and contact center

Replace static recorded prompts with dynamic speech output that can say what each caller needs to hear.

Accessibility and audio content

Read on-screen text aloud and generate audio for articles, notifications, and training material on demand.

See demo

Type it. Hear it.

Demo the Text-to-Speech API in action. See how text is turned into streamed speech audio that begins playing almost instantly.

Sign-up or login is required to access the portal.

Try the playground

Developer first

Start streaming in minutes

Simple, well-documented APIs
Flat JSON request body, plain-text input
Streamed raw audio, no envelope to parse
Clear, structured error handling

See API docs

# Convert text to speech

curl -X POST \
  https://api.zoom.us/v2/aiservices/tts/synthesize \
  -H "Authorization: Bearer $YOUR_JWT_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{ "input": "Hello from Zoom AI Services." }' \
  --output speech.pcm

# Convert text to speech

import requests

response = requests.post(
"https://api.zoom.us/v2/aiservices/tts/synthesize",
    headers={"Authorization": "Bearer YOUR_JWT_TOKEN"},
    json={"input": "Hello from Zoom AI Services."},
    stream=True,
)
response.raise_for_status()
with open("speech.pcm", "wb") as f:
    for chunk in response.iter_content(chunk_size=8192):
        f.write(chunk)

# Convert text to speech

import fs from 'node:fs';
import { Readable } from 'node:stream';
import { pipeline } from 'node:stream/promises';
const response = await fetch('https://api.zoom.us/v2/aiservices/tts/synthesize', {
    method: 'POST',
    headers: {Authorization: 'Bearer YOUR_JWT_TOKEN', 'Content-Type': 'application/json'},
    body: JSON.stringify({ input: 'Hello from Zoom AI Services.' }),
});
if (!response.ok) throw new Error(await response.text());
await pipeline(Readable.fromWeb(response.body), fs.createWriteStream('speech.pcm'));

Pricing

Straightforward pricing

Apply prepaid Zoom Build Platform Credits to your use of Text-to-Speech API based on the rates below.

Text-to-Speech API Fast

$20/1M characters

Text-to-Speech API (Fast) converts written text into natural-sounding speech audio in seconds with customizable voices, tones and engaging audio content delivery.

Usage is measured based on the total number of input characters submitted for speech synthesis during a given billing period.

Get started