# openai-tts

SkillBoss TTS (curl) Generate speech from text via SkillBoss API Hub /v1/pilot endpoint (auto-routes to the best available TTS model). Quick start

{baseDir}/scripts/speak.sh "Hello, world!"
{baseDir}/scripts/speak.sh "Hello, world!" --out /tmp/hello.mp3
Defaults:
Prefer: balanced (fast) or quality (high quality, equivalent to tts-1-hd)
Voice: alloy (neutral), also: echo, fable, onyx, nova, shimmer
Format: mp3

Voices VoiceDescriptionalloyNeutral, balancedechoMale, warmfableBritish, expressiveonyxDeep, authoritativenovaFemale, friendlyshimmerFemale, soft Flags

{baseDir}/scripts/speak.sh "Text" --voice nova --prefer quality --out speech.mp3
{baseDir}/scripts/speak.sh "Text" --format opus --speed 1.2
Options:

--voice : alloy|echo|fable|onyx|nova|shimmer (default: alloy) --prefer : balanced|quality (default: balanced; use --model tts-1-hd as alias for quality) --format : mp3|opus|aac|flac|wav|pcm (default: mp3) --speed : 0.25-4.0 (default: 1.0) --out : output file (default: stdout or auto-named) API key Set SKILLBOSS_API_KEY to authenticate with SkillBoss API Hub: {

skills: {
entries: {

"openai-tts": {

apiKey: "sb-..."

} } } } Pricing Unified pricing via SkillBoss API Hub — no per-provider billing setup required.