Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.oneinbox.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
Before you start

Built-in voices work out of the box — set tts.voice_id when you create an agent. Custom voices need a third-party provider integration first (e.g. ElevenLabs, Cartesia).
1

1. List available voices

# All voices
curl https://api.oneinbox.ai/v1/voices \
  -H "Authorization: Bearer <api_key>"

# Filter by provider
curl "https://api.oneinbox.ai/v1/voices?provider=cartesia" \
  -H "Authorization: Bearer <api_key>"
Pick a voice_id and use it in your agent’s tts block.
2

2. Import a custom voice (optional)

Goal: Clone or import a voice from a third-party provider (e.g. ElevenLabs, Cartesia).First, add an integration for your provider. Then:
curl -X POST https://api.oneinbox.ai/v1/voices/import \
  -H "Authorization: Bearer <api_key>" \
  -H "Content-Type: application/json" \
  -d '{
    "provider": "elevenlabs",
    "provider_voice_id": "21m00Tcm4TlvDq8ikWAM",
    "name": "Rachel (cloned)",
    "credential_id": "<credential_id>",
    "gender": "female",
    "language": "en",
    "accent": "American"
  }'
3

3. Override voice on a single call (optional)

When creating a web call, you can override TTS without changing the agent — see Start web call for override fields from third-party providers (e.g. ElevenLabs, Cartesia).

​
API reference

List voices · Import voice