SDKs & Snippets

Phonetico's API is plain HTTP. Any HTTP client works. We don't ship official SDKs yet; the snippets below cover the core POST /v1/asr/upload (ASR) and POST /v1/tts (TTS) calls in the languages developers ask about most.

Replace pk_live_your_key_here with a key from /keys and amh with any supported locale.

Transcribe a file

curl -X POST https://api.phonetico.ai/v1/asr/upload \
  -H "Authorization: Bearer pk_live_your_key_here" \
  -F "[email protected]" \
  -F "localeCode=amh"

Word timestamps (JSON endpoint)

Use the JSON endpoint when you need wordTimestamps. The audio is base64-encoded in the body.

curl -X POST https://api.phonetico.ai/v1/asr \
  -H "Authorization: Bearer pk_live_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "audio": "'$(base64 -i speech.wav)'",
    "localeCode": "amh",
    "wordTimestamps": true
  }'

Synthesizing text with a preset voice

The simplest TTS path: pass a voice.preset from GET /v1/tts/voices and the text to speak. No reference audio, no rights attestation. Consent travelled with the voice when it was registered. Tigrinya only today; voice tir_phonetico_01 is seeded.

curl -X POST https://api.phonetico.ai/v1/tts \
  -H "Authorization: Bearer pk_live_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "ምስ መኪና ስለዘላተሙኒ ውነይ ስሒተ።",
    "language": "tir",
    "voice": { "preset": "tir_phonetico_01" },
    "options": { "qualityTier": "balanced" }
  }' | jq -r '.audio' | base64 -d > out.wav

Synthesizing text in a custom voice

Same key, same auth, JSON body that carries a reference clip plus its transcript. Tigrinya only today; other locales return 503 until their finetune lands.

REF_AUDIO=$(base64 -i voice-sample.wav)
curl -X POST https://api.phonetico.ai/v1/tts \
  -H "Authorization: Bearer pk_live_your_key_here" \
  -H "Content-Type: application/json" \
  -d @- <<JSON | jq -r '.audio' | base64 -d > out.wav
{
  "text": "ምስ መኪና ስለዘላተሙኒ ውነይ ስሒተ።",
  "language": "tir",
  "voice": {
    "reference": {
      "audio": "$REF_AUDIO",
      "transcript": "exact transcript of voice-sample.wav",
      "rightsAttestation": true
    }
  },
  "options": { "qualityTier": "balanced" }
}
JSON

Community SDKs

Building one? We're happy to link community libraries here. Send us a link and we'll add it.