Speechbase
Models
OpenAI

openai/

OpenAI TTS-1

Public model reference for openai/tts-1: Speechbase pricing, BYOK fee, timestamp behavior, language coverage, and quick-start code.

openai/tts-1
QuickstartProvider docs
Pricing

Managed routing

Speech only
$29 / 1M chars
With timestamps
$38 / 1M chars

Speechbase pays the provider; you spend credits.

BYOK

Platform fee
3.4%
Speech only
0.99 cr / 1K chars

Your provider key pays upstream; Speechbase charges the platform fee.

This model uses Speechbase's timestamp recovery pass when word-level timing is requested, so its with-timestamps price is higher than speech-only generation.

Capabilities
StreamingSupported
Audio tagsNot supported
Voice cloningNot supported
Open sourceNot supported
Quick start
import { writeFileSync } from "node:fs";
import { generateSpeech } from "@speech-sdk/core";

const result = await generateSpeech({
  model: "openai/tts-1",
  voice: "your-provider-voice-id",
  text: "Hello from Speechbase.",
  output: { format: "mp3" },
});

writeFileSync("hello.mp3", result.audio.uint8Array);
curl -X POST https://api.speechbase.ai/v1/audio/speech \
  -H "Authorization: Bearer $SPEECHBASE_API_KEY" \
  -H "Content-Type: application/json" \
  --output hello.mp3 \
  -d '{
    "model": "openai/tts-1",
    "voice": "your-provider-voice-id",
    "text": "Hello from Speechbase.",
    "output": "mp3"
  }'