কণ্ঠস্বর প্রতিলিপি

import base64
from google import genai

client = genai.Client()

with open("reference_speaker.wav", "rb") as f:
    source_b64 = base64.b64encode(f.read()).decode("utf-8")

with open("speaker_consent.wav", "rb") as f:
    consent_b64 = base64.b64encode(f.read()).decode("utf-8")

# Create a persistent replicated voice (store=True)
replicated_voice = client.voices.create(
    store=True,
    voice={
        "model": "gemini-3.8-flash-tts",
        "type": "replicated",
        "display_name": "Custom Replicated Speaker",
        "replicated": {
            "source_audio": {
                "mime_type": "audio/wav",
                "data": source_b64,
            },
            "consent_audio": {
                "mime_type": "audio/wav",
                "data": consent_b64,
            },
        },
    },
)

print(f"Created voice ID: {replicated_voice.id}")

import * as fs from "node:fs";
import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI();

const sourceB64 = fs.readFileSync("reference_speaker.wav").toString("base64");
const consentB64 = fs.readFileSync("speaker_consent.wav").toString("base64");

// Create a persistent replicated voice (store: true)
const replicatedVoice = await ai.voices.create({
  store: true,
  voice: {
    model: "gemini-3.8-flash-tts",
    type: "replicated",
    display_name: "Custom Replicated Speaker",
    replicated: {
      source_audio: {
        mime_type: "audio/wav",
        data: sourceB64,
      },
      consent_audio: {
        mime_type: "audio/wav",
        data: consentB64,
      },
    },
  },
});

console.log(`Created voice ID: ${replicatedVoice.id}`);

SOURCE_B64=$(base64 -w 0 reference_speaker.wav)
CONSENT_B64=$(base64 -w 0 speaker_consent.wav)

curl "https://generativelanguage.googleapis.com/v1beta/voices" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -X POST \
  -d "{
    \"store\": true,
    \"voice\": {
      \"model\": \"gemini-3.8-flash-tts\",
      \"type\": \"replicated\",
      \"display_name\": \"Custom Replicated Speaker\",
      \"replicated\": {
        \"source_audio\": {
          \"mime_type\": \"audio/wav\",
          \"data\": \"$SOURCE_B64\"
        },
        \"consent_audio\": {
          \"mime_type\": \"audio/wav\",
          \"data\": \"$CONSENT_B64\"
        }
      }
    }
  }"

import base64
from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.8-flash-tts",
    input=[{
        "type": "user_input",
        "content": [{
            "type": "text",
            "text": (
                "Hello! This audio was synthesized using a replicated"
                " speaker voice."
            ),
            "annotations": [{
                "type": "speech_metadata",
                "style": "warm and conversational",
            }],
        }],
    }],
    response_format={"type": "audio"},
    generation_config={
        "speech_config": [
            {"voice": replicated_voice.id},
        ]
    },
)

with open("replicated_speech.wav", "wb") as f:
    f.write(base64.b64decode(interaction.output_audio.data))

import * as fs from "node:fs";
import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI();

const interaction = await ai.interactions.create({
  model: "gemini-3.8-flash-tts",
  input: [{
    type: "user_input",
    content: [{
      type: "text",
      text: "Hello! This audio was synthesized using a replicated speaker voice.",
      annotations: [{
        type: "speech_metadata",
        style: "warm and conversational",
      }],
    }],
  }],
  response_format: { type: "audio" },
  generation_config: {
    speech_config: [
      { voice: replicatedVoice.id },
    ],
  },
});

fs.writeFileSync("replicated_speech.wav", Buffer.from(interaction.output_audio.data, "base64"));

curl "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -X POST \
  -d '{
    "model": "gemini-3.8-flash-tts",
    "input": [{
      "type": "user_input",
      "content": [{
        "type": "text",
        "text": "Hello! This audio was synthesized using a replicated speaker voice.",
        "annotations": [{
          "type": "speech_metadata",
          "style": "warm and conversational"
        }]
      }]
    }],
    "response_format": {"type": "audio"},
    "generation_config": {
      "speech_config": [
        {"voice": "voice_YOUR_REPLICATED_VOICE_ID"}
      ]
    }
  }'

from google import genai

client = genai.Client()

# List stored replicated voices in your project
response = client.voices.list(type_=["replicated"])
for voice in response.voices or []:
    print(voice.id, voice.display_name, voice.type)

# Retrieve a specific voice by ID
voice_details = client.voices.get(id=replicated_voice.id)

# Delete a stored replicated voice
client.voices.delete(id=replicated_voice.id)

import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI();

// List stored replicated voices in your project
const response = await ai.voices.list({ type: ["replicated"] });
for (const voice of response.voices ?? []) {
  console.log(voice.id, voice.display_name, voice.type);
}

// Retrieve a specific voice by ID
const voiceDetails = await ai.voices.get(replicatedVoice.id);

// Delete a stored replicated voice
await ai.voices.delete(replicatedVoice.id);

# List stored replicated voices in your project
curl -G "https://generativelanguage.googleapis.com/v1beta/voices" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  --data-urlencode "type=replicated"

# Retrieve a specific voice by ID
curl "https://generativelanguage.googleapis.com/v1beta/voices/voice_YOUR_REPLICATED_VOICE_ID" \
  -H "x-goog-api-key: $GEMINI_API_KEY"

# Delete a stored replicated voice
curl -X DELETE "https://generativelanguage.googleapis.com/v1beta/voices/voice_YOUR_REPLICATED_VOICE_ID" \
  -H "x-goog-api-key: $GEMINI_API_KEY"

import base64
from google import genai

client = genai.Client()

with open("reference_speaker.wav", "rb") as f:
    source_b64 = base64.b64encode(f.read()).decode("utf-8")

with open("speaker_consent.wav", "rb") as f:
    consent_b64 = base64.b64encode(f.read()).decode("utf-8")

# Create a stateless client-managed voice key (store=False)
replicated_voice = client.voices.create(
    store=False,
    voice={
        "model": "gemini-3.8-flash-tts",
        "type": "replicated",
        "replicated": {
            "source_audio": {"mime_type": "audio/wav", "data": source_b64},
            "consent_audio": {"mime_type": "audio/wav", "data": consent_b64},
        },
    },
)

# Pass replicated_voice.key ("voicekey_...") directly as the speaker voice
interaction = client.interactions.create(
    model="gemini-3.8-flash-tts",
    input=[{
        "type": "user_input",
        "content": [{
            "type": "text",
            "text": "Hello! This audio uses a stateless client-managed voice key.",
            "annotations": [{
                "type": "speech_metadata",
                "style": "warm and conversational",
            }],
        }],
    }],
    response_format={"type": "audio"},
    generation_config={
        "speech_config": [
            {"voice": replicated_voice.key},
        ]
    },
)

import * as fs from "node:fs";
import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI();

const sourceB64 = fs.readFileSync("reference_speaker.wav").toString("base64");
const consentB64 = fs.readFileSync("speaker_consent.wav").toString("base64");

// Create a stateless client-managed voice key (store: false)
const replicatedVoice = await ai.voices.create({
  store: false,
  voice: {
    model: "gemini-3.8-flash-tts",
    type: "replicated",
    replicated: {
      source_audio: { mime_type: "audio/wav", data: sourceB64 },
      consent_audio: { mime_type: "audio/wav", data: consentB64 },
    },
  },
});

// Pass replicatedVoice.key ("voicekey_...") directly as the speaker voice
const interaction = await ai.interactions.create({
  model: "gemini-3.8-flash-tts",
  input: [{
    type: "user_input",
    content: [{
      type: "text",
      text: "Hello! This audio uses a stateless client-managed voice key.",
      annotations: [{
        type: "speech_metadata",
        style: "warm and conversational",
      }],
    }],
  }],
  response_format: { type: "audio" },
  generation_config: {
    speech_config: [
      { voice: replicatedVoice.key },
    ],
  },
});

SOURCE_B64=$(base64 -w 0 reference_speaker.wav)
CONSENT_B64=$(base64 -w 0 speaker_consent.wav)

curl "https://generativelanguage.googleapis.com/v1beta/voices" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -X POST \
  -d "{
    \"store\": false,
    \"voice\": {
      \"model\": \"gemini-3.8-flash-tts\",
      \"type\": \"replicated\",
      \"replicated\": {
        \"source_audio\": {\"mime_type\": \"audio/wav\", \"data\": \"$SOURCE_B64\"},
        \"consent_audio\": {\"mime_type\": \"audio/wav\", \"data\": \"$CONSENT_B64\"}
      }
    }
  }"