Voice Localization

curl --fail --silent --show-error --max-time 30 -X POST https://api.gradium.ai/api/voice-generator/localize \
  -H "x-api-key: $GRADIUM_API_KEY" \
  -H "Content-Type: application/json" \
  -d "{
    \"src_voice\": \"$SOURCE\",
    \"target_language\": \"en\",
    \"accent\": \"General American\",
    \"gender\": \"female\",
    \"n_samples\": 2
  }" > candidates.json

CAND0=$(jq -r '.embeddings[0].embedding_id' candidates.json)

import os
import requests

API_KEY = os.environ["GRADIUM_API_KEY"]
BASE = "https://api.gradium.ai/api"
SOURCE = os.environ["SOURCE"]  # a voice id or a vox_emb_ candidate id

resp = requests.post(
    f"{BASE}/voice-generator/localize",
    json={
        "src_voice": SOURCE,
        "target_language": "en",
        "accent": "General American",
        "gender": "female",
        "n_samples": 2,
    },
    headers={"x-api-key": API_KEY},
    timeout=30,
)
resp.raise_for_status()
candidates = [e["embedding_id"] for e in resp.json()["embeddings"]]

wait_for_candidate() {
  local deadline=$((SECONDS + 120))
  local result
  while (( SECONDS < deadline )); do
    result=$(curl --fail --silent --show-error --max-time 10 \
      -H "x-api-key: $GRADIUM_API_KEY" \
      "https://api.gradium.ai/api/voice-generator/embeddings?embedding_id=$1") || return 1
    if ! jq -e '.embeddings | length > 0' <<< "$result" > /dev/null; then
      echo "Candidate not found: $1" >&2
      return 1
    fi
    if jq -e '.embeddings[0].ready' <<< "$result" > /dev/null; then
      return 0
    fi
    sleep 2
  done
  echo "Timed out waiting for candidate: $1" >&2
  return 1
}
wait_for_candidate "$CAND0"

import time

def wait_until_ready(embedding_id, timeout_s=120):
    deadline = time.monotonic() + timeout_s
    while time.monotonic() < deadline:
        resp = requests.get(
            f"{BASE}/voice-generator/embeddings",
            params={"embedding_id": embedding_id},
            headers={"x-api-key": API_KEY},
            timeout=min(10, max(0.1, deadline - time.monotonic())),
        )
        resp.raise_for_status()
        found = resp.json()["embeddings"]
        if not found:
            raise RuntimeError(f"candidate {embedding_id} not found")
        if found and found[0]["ready"]:
            return found[0]
        time.sleep(2)
    raise TimeoutError(embedding_id)

for embedding_id in candidates:
    wait_until_ready(embedding_id)

curl --fail --silent --show-error --max-time 30 -X POST https://api.gradium.ai/api/post/speech/tts \
  -H "x-api-key: $GRADIUM_API_KEY" \
  -H "Content-Type: application/json" \
  -d "{
    \"text\": \"Hi, this is Constance. Same voice, new language, and hopefully the same personality.\",
    \"voice_id\": \"$CAND0\",
    \"model_name\": \"default\",
    \"output_format\": \"wav\",
    \"only_audio\": true
  }" --output candidate-0.wav

resp = requests.post(
    f"{BASE}/post/speech/tts",
    json={
        "text": "Hi, this is Constance. Same voice, new language, and hopefully the same personality.",
        "voice_id": candidates[0],
        "model_name": "default",
        "output_format": "wav",
        "only_audio": True,
    },
    headers={"x-api-key": API_KEY},
    timeout=30,
)
resp.raise_for_status()
with open("candidate-0.wav", "wb") as f:
    f.write(resp.content)

curl --fail --silent --show-error --max-time 30 -X POST https://api.gradium.ai/api/voices/from-embedding \
  -H "x-api-key: $GRADIUM_API_KEY" \
  -H "Content-Type: application/json" \
  -d "{
    \"voxium_embedding_id\": \"$CAND0\",
    \"name\": \"Constance EN\",
    \"description\": \"French support voice, localized to General American\"
  }" > voice.json

VOICE=$(jq -r '.uid' voice.json)

resp = requests.post(
    f"{BASE}/voices/from-embedding",
    json={
        "voxium_embedding_id": candidates[0],
        "name": "Constance EN",
        "description": "French support voice, localized to General American",
    },
    headers={"x-api-key": API_KEY},
    timeout=30,
)
resp.raise_for_status()
voice_id = resp.json()["uid"]