Cast
Cinematic, emotional long-form TTS for podcasts, narration, and audiobooks.
Cast is our async, emotional text-to-speech engine built for long-form production: podcasts, narration, audiobooks, and brand audio. Expressive voices, included commercial rights, and the free Voice Designer let you direct tone, pacing, and character without a studio.
- Price
- $0.02/min
- Endpoint
POST /v1/audio/speech- Scope
voice:synthesize- Model id
pyai-voice
Hear the voices first.
Tap a voice for an instant sample from the same catalog Cast uses for narration, podcasts, and audiobooks.
Open the PlaygroundWhat you get
Direction, not just generation
Guide delivery with emotion, pacing, and performance notes instead of settling for a flat narrator.
Designed voices included
Create brand, character, and narrator voices for free; pay only for the audio you render.
Plan long-form production simply
Billed per finished minute, with no credit math or character counting.
Capabilities
- Predictable long-form pricing
- Commercial rights included
- Voice Designer (free)
- Voice cloning (free)
- Podcast + audiobook workflows
Async synthesis is optimized for quality and long-form cost. Realtime Speak remains available for low-latency playback.
Start in minutes
curl https://api.pyai.com/v1/audio/speech \
-H "Authorization: Bearer $PYAI_KEY" \
-d '{"model":"pyai-voice","voice":"stock_ava_en_us","input":"Read this like a warm documentary narrator."}' \
--output chapter.mp3FAQ
How is Cast different from Speak?
Speak is the realtime TTS API. Cast is the long-form workflow for podcasts, narration, and audiobooks - built on async synthesis, emotional direction, and Voice Designer.
What does Voice Designer cost?
Voice design and cloning enrollment are free; Cast audio is billed per minute with commercial rights included. Check our pricing page for details.
Build with Cast today.
Start free with $50.00 in credit - no card. Your test key works instantly.
No credit card - OpenAI-compatible - cancel anytime