Production-ready voice API
Reliable voice AI for products that speak.
Generate speech that is operationally reliable and easy to integrate, with transparent request cost and explicit generation states for developers before they build.
Signup gives $1.00 in credits. No card required.
POST /v1/tts/generate
Authorization: Bearer lv_live_YOUR_API_KEY
Content-Type: application/json
{
"text": "Reliable voice AI for products that speak. This output is tuned for docs, onboarding, and customer-facing messaging.",
"model": "pro",
"voice": "narrator_warm_male",
"language": "en"
}SDK quickstart
Use one of the SDK entry points below to move from request → response in minutes.
# Install: no SDK required
curl -X POST https://api.leanvox.com/v1/tts/generate \
-H "Authorization: Bearer lv_live_YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"text": "Reliable voice AI for products that speak.",
"model": "pro",
"voice": "narrator_warm_male",
"language": "en"
}'Voice capability
Choose the model class that matches your reliability and quality target.
Standard
Low-latency production baseline with practical costs.
$0.0024 / 1K chars
Latency: Sub-200ms
Voices: 54+
Languages: 10
- Fastest path for high-volume notifications
- Clustering and retries for API stability
- Streaming response support
Pro
Production-grade quality with emotional control and cloning support.
$0.0059 / 1K chars
Latency: 180-260ms
Voices: 12+ curated
Languages: 23
- Voice cloning from 10 seconds of audio
- Paralinguistic tags for expression
- High fidelity streaming chunks
Max
Text-guided voice creation for product-specific brand timbre.
Custom voice requests
Latency: 400ms+
Voices: Unlimited (designed + remix)
Languages: 23
- Prompt-based custom voices
- Per-request design controls
- Used for branded narration and characters
Pricing clarity
Transparent credit usage with predictable pricing before generation.
Signup bonus: $1.00
Estimate before you generate
Calculator rounds up to 1K-character billing blocks and excludes promotional bonuses.
Voice preview library
Listen to curated samples from Standard, Pro, and Max routes.
Operational trust
Compact proof points for teams evaluating production use.
Service objective for production API availability.
Use docs/status links for incident and maintenance visibility.
Responses surface request timing so teams can track real app latency.
Retention and deletion controls live in privacy/docs, not hidden sales copy.
Privacy messaging stays explicit and conservative until contract terms say more.
Higher limits and formal SLA notes belong in enterprise discussions.
Reliability and comparison
Infrastructure and API behavior first, not marketing claims.
| Metric | LeanVox | Competitor average | Why we track it |
|---|---|---|---|
| Per-1K character pricing | $0.0024 – $0.01 | Higher or tier-restricted | Transparent usage-first pricing. |
| API delivery mode | Streaming + request metadata | Inconsistent response contracts | Generated state and cost in response path. |
| Language coverage | 23 | Varies | Measured multilingual support in production. |
| Operational reliability | 99.9% target uptime | Published per usage only | Simple status + latency indicators everywhere. |
Start with proven workflow output
Generate in the API first, then ship to products with full visibility into cost and latency.