Chirp 3: Benutzerdefinierte Stimme für sofortige Nutzung

Mit Sammlungen den Überblick behalten Sie können Inhalte basierend auf Ihren Einstellungen speichern und kategorisieren.

import requests, os, json

def create_instant_custom_voice_key(
    access_token, project_id, reference_audio_bytes, consent_audio_bytes
):
    url = "https://texttospeech.googleapis.com/v1beta1/voices:generateVoiceCloningKey"

    request_body = {
        "reference_audio": {
            "audio_config": {"audio_encoding": "LINEAR16", "sample_rate_hertz": 24000},
            "content": reference_audio_bytes,
        },
        "voice_talent_consent": {
            "audio_config": {"audio_encoding": "LINEAR16", "sample_rate_hertz": 24000},
            "content": consent_audio_bytes,
        },
        "consent_script": "I am the owner of this voice and I consent to Google using this voice to create a synthetic voice model.",
        "language_code": "en-US",
    }

    try:
        headers = {
            "Authorization": f"Bearer {access_token}",
            "x-goog-user-project": project_id,
            "Content-Type": "application/json; charset=utf-8",
        }

        response = requests.post(url, headers=headers, json=request_body)
        response.raise_for_status()

        response_json = response.json()
        return response_json.get("voiceCloningKey")

    except requests.exceptions.RequestException as e:
        print(f"Error making API request: {e}")
    except json.JSONDecodeError as e:
        print(f"Error decoding JSON response: {e}")
    except Exception as e:
        print(f"An unexpected error occurred: {e}")

import requests, os, json, base64
from IPython.display import Audio, display

def synthesize_text_with_cloned_voice(access_token, project_id, voice_key, text):
    url = "https://texttospeech.googleapis.com/v1beta1/text:synthesize"

    request_body = {
        "input": {
            "text": text
        },
        "voice": {
            "language_code": "en-US",
            "voice_clone": {
                "voice_cloning_key": voice_key,
            }
        },
        "audioConfig": {
            "audioEncoding": "LINEAR16",
            "sample_rate_hertz": 24000
        }
    }

    try:
        headers = {
            "Authorization": f"Bearer {access_token}",
            "x-goog-user-project": project_id,
            "Content-Type": "application/json; charset=utf-8"
        }

        response = requests.post(url, headers=headers, json=request_body)
        response.raise_for_status()

        response_json = response.json()
        audio_content = response_json.get("audioContent")

        if audio_content:
            display(Audio(base64.b64decode(audio_content), rate=24000))
        else:
            print("Error: Audio content not found in the response.")
            print(response_json)

    except requests.exceptions.RequestException as e:
        print(f"Error making API request: {e}")
    except json.JSONDecodeError as e:
        print(f"Error decoding JSON response: {e}")
    except Exception as e:
        print(f"An unexpected error occurred: {e}")