Skip to main content
All examples use the base URL https://api.hedra.com/web-app/public and require an X-API-Key header. 
export HEDRA_API_KEY="your_api_key"

​
Step 1: Pick a voice

List available voices: 
curl https://api.hedra.com/web-app/public/voices \
  -H "X-API-Key: $HEDRA_API_KEY"

​
Step 2: Generate speech

curl -X POST https://api.hedra.com/web-app/public/generations \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $HEDRA_API_KEY" \
  -d '{
    "type": "text_to_speech",
    "voice_id": "f412c62f-e94f-41c0-bfc6-97f63289941c",
    "text": "Hello, welcome to Hedra! This is an example of text-to-speech generation.",
    "stability": 0.5,
    "speed": 1.0,
    "language": "English"
  }'

​
Required fields

FieldDescription
typeSet to "text_to_speech"
voice_idThe voice to use (from GET /voices)
textThe text to convert to speech

​
Optional fields

FieldDescription
stability0.0 (most stable) to 1.0 (most variable). Default: 1.0
speed0.7 (slowest) to 1.2 (fastest). Default: 1.0
languagee.g. "English", "Spanish", "French", "Japanese". Default: "auto"

​
Step 3: Poll for completion

curl https://api.hedra.com/web-app/public/generations/{generation_id}/status \
  -H "X-API-Key: $HEDRA_API_KEY"
When status is "complete", the response includes an asset_id for the generated audio file.

​
Clone a voice

You can create a custom voice by uploading an audio sample and cloning it.

​
1. Upload an audio sample

curl -X POST https://api.hedra.com/web-app/public/assets \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $HEDRA_API_KEY" \
  -d '{
    "name": "voice-sample.mp3",
    "type": "audio"
  }'

curl -X POST https://api.hedra.com/web-app/public/assets/{asset_id}/upload \
  -H "X-API-Key: $HEDRA_API_KEY" \
  -F "file=@/path/to/voice-sample.mp3"

​
2. Clone the voice

curl -X POST https://api.hedra.com/web-app/public/generations \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $HEDRA_API_KEY" \
  -d '{
    "type": "voice_clone",
    "audio_id": "{audio_asset_id}",
    "name": "My Custom Voice"
  }'
Once complete, the response includes an asset_id for the new voice. Use this as the voice_id in text-to-speech requests.