Welcome to Destined Voice API
Destined Voice provides enterprise-grade Text-to-Speech (TTS) with the largest collection of consented, diverse speaker voices available via API.Why Destined Voice?
10,000+ Real Voices
Diverse demographics including gender, age, region, and accent. All voices are from consented speakers.
Voice Generation
Generate new custom voices for your evals.
Voice Agent Evals
Evaluate 9+ speech-to-text providers with WER/CER metrics and demographic bias analysis.
Batch Processing
Generate audio for multiple speakers asynchronously with job tracking.
Quick Example
Features
| Feature | Description |
|---|---|
| TTS Synthesis | Convert text to natural speech using any speaker voice |
| Speaker Browse | Filter speakers by gender, age, region, accent |
| Batch Jobs | Process multiple synthesis requests asynchronously |
| STT Evaluation | Test 9 providers: Deepgram, AssemblyAI, OpenAI, Google, Azure, Amazon, Soniox, Play.ht |
| Dataset Import | Upload CSV files for bulk TTS generation |
| Usage Tracking | Monitor character usage and API calls |
Pricing
| Feature | Starter | Pro | Enterprise |
|---|---|---|---|
| Price | $0/month | $500/month | $5,000/month |
| Evals/month | 1 | Unlimited | Unlimited |
| Characters | 1,000 | 100,000 | 1,000,000 |
| Real voices | 500 | 5,000 | 10,000+ |
| Custom voices | Unlimited | Unlimited | Unlimited |