Models and Pricing
Text to Speech
The Text to Speech API converts text into natural speech, billed per input character. Supports multiple voices, streaming and batch output, in MP3, WAV, PCM, μ-law, and A-law formats.
How to increase my rate limits?
At a glance
| Details | |
|---|---|
| Modalities | Text → Audio |
| Pricing | $4.20 / 1M characters |
| Region | us-east-1 |
Pricing
| Details | |
|---|---|
| Per 1M characters | $4.20 / 1M characters |
Rate Limits
| Details | |
|---|---|
| Requests per minute | 3,000 RPM |
| Requests per second | 50 RPS |
| Concurrent sessions | 100 per team |
Capabilities
- Multiple voices
- Streaming output
- Batch output
- MP3 / WAV / PCM / μ-law / A-law formats
Availability
| Details | |
|---|---|
| Cluster | us-east-1 |
Documentation
- Text to Speech Guide — Getting started with text to speech
- API Reference — Text to Speech endpoint reference
- Models and Pricing — Full pricing overview
Did you find this page helpful?
Last updated: April 15, 2026