TTS-1
Quick, low-cost speech from text, for real-time voice.
About TTS-1
TTS-1 turns text into spoken audio fast enough for a live conversation. It comes with nine built-in voices, including alloy, nova and shimmer, and returns MP3, Opus, AAC, FLAC, WAV or raw PCM.
Speed is the trade: OpenAI says it is lower quality than its HD sibling, and unlike OpenAI’s newer speech models you cannot direct its tone or accent. For read-aloud features, voice replies and prototypes it is the inexpensive, dependable choice.
Where it’s strong
Voice replies in real time.
Reading app content aloud.
Low-cost narration and prototypes.
Where to be careful
Audio quality is below OpenAI’s HD and newer speech models.
Voices are tuned for English. Other languages work but can sound less natural.
Up to 4,096 characters per request, so long text has to be split.
Price
Every rate is published and stays the same from one request to the next. See every model.
Specs
tts-1Call it
Use the OpenAI SDK you already have — point it at Roar AI and name the model. Read the docs.
from openai import OpenAI
client = OpenAI(base_url="https://api.roar-ai.com/v1", api_key="roar_live_…")
audio = client.audio.speech.create(
model="tts-1",
voice="alloy",
input="Your order has been dispatched.",
)Questions
How much does TTS-1 cost?
Price is $17.25 per 1M characters. The rate is published and does not change from one request to the next.
Can I use TTS-1 alongside other models?
Yes. Every model on Roar AI is on the same API key and the same monthly invoice, so switching from TTS-1 to another model is a change to one word in your code.
Is TTS-1 open source?
No. OpenAI does not publish the weights, so it is only available through an API like this one.