Skip to main content
This guide takes you from an API key to synthesized audio, then to a low-latency stream.

Prerequisites

1

Create an API key

Sign in to the Chariot dashboard and generate an API key. Copy it somewhere safe, you send it on every request.
2

Pick a voice

List the available voices and copy a voice_id:

Synthesize speech

Send text to POST /v1/tts and save the returned WAV:
The audio comes back as the response body. The Credit-Utilized header reports the cost (1 credit per character).

Stream for low latency

For real-time playback, use POST /v1/tts/stream. It returns raw 16-bit PCM at 44.1 kHz as it is generated, so you can start playing before synthesis finishes:
Python
The stream is headerless PCM (audio/L16, 44100 Hz, mono, signed 16-bit little-endian), not a WAV file. Your player must be configured for that format, or you must prepend a WAV header yourself. The fully assembled WAV is also available at the X-audio-url header once the stream completes.

Next steps

Choose your API

When to use REST, HTTP streaming, or WebSocket.

WebSocket streaming

Send text incrementally over a persistent connection.

Errors & status codes

Handle failures gracefully.

Credits & pricing

Understand what each request costs.