Text to Speech API
Convert text to speech with multiple voice routes, async tasks, and voice-specific controls.
What is Text to Speech API?
CheapAI exposes multiple text-to-speech routes for different voice engines and use cases. Submit a task, then poll or receive a webhook when the audio is ready.
Supported Models
Voice task routes
Use the route that matches your voice engine and output needs
Voice-id routes
Create TTS tasks by voice id with task polling
Alternate TTS namespaces
Additional routes with configurable voice settings
Edge TTS
Large voice catalog with transcript support
Quick Start
curl -X POST "https://api.cheapaiapi.com/v1/text-to-speech/21m00Tcm4TlvDq8ikWAM?output_format=mp3_44100_128" \
-H "Authorization: Bearer sk_your_api_key" \
-H "Content-Type: application/json" \
-d '{
"text": "Hello! Welcome to CheapAI.",
"model_id": "eleven_multilingual_v2"
}'Why CheapAI?
Multiple Voice Engines
Use the namespace and route that matches your TTS workflow.
Async Delivery
Get task ids back immediately, then poll or receive a webhook.
Transcript Support
Some routes support subtitle or transcript outputs alongside the audio.
Voice Controls
Tune voice settings, speed, and route-specific options where supported.
Async
Flow
Yes
Webhook Ready
Route Based
Transcript Support
Multi-Route
Voice Catalog
Frequently Asked Questions
How do I retrieve the generated audio?expand_more
Poll the task endpoint until it is done, then read the returned metadata URLs.
Can I use my own cloned voice?expand_more
Yes, where the selected route supports voice cloning or custom voice ids.
Do all TTS routes behave the same?expand_more
No. Different routes expose different namespaces and option sets depending on the workflow.
Start Building Today
Get $2 in free credits. Create an API key, set spend controls if needed, and start testing the current task-based endpoints.
Get API Key arrow_forward