VibeVoice 1.5B
ᠵᡠᠸᡝᠪᡠᠮᠪᡳ
vibevoice
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/vibevoice?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"script": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
"speakers": [
{
"preset": "Frank [EN]"
},
{
"preset": "Carter [EN]"
}
]
}'
# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY"
const API = "https://api.doitong.com/v1";
const headers = {
"Authorization": "Bearer " + process.env.DOITONG_API_KEY,
"Content-Type": "application/json",
};
// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/vibevoice?wait=20", {
method: "POST",
headers,
body: JSON.stringify({
"script": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
"speakers": [
{
"preset": "Frank [EN]"
},
{
"preset": "Carter [EN]"
}
]
}),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);
// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
import os
import requests
API = "https://api.doitong.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}
payload = {
"script": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
"speakers": [
{
"preset": "Frank [EN]",
},
{
"preset": "Carter [EN]",
},
],
}
# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/vibevoice", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])
# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
# 1. Connect once (Claude Code; Cursor, VS Code, Claude Desktop: https://doitong.com/mnc/developers/docs/mcp)
claude mcp add --transport http doitong-models https://api.doitong.com/v1/mcp \
--header "Authorization: Bearer $DOITONG_API_KEY"
# 2. Your agent calls the "run" tool with:
{
"model_id": "vibevoice",
"input": {
"script": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
"speakers": [
{
"preset": "Frank [EN]"
},
{
"preset": "Carter [EN]"
}
]
}
}
VibeVoice 1.5B ᠮᠣᠳᡝᠯ (vibevoice) ᠪᡝ Doitong API ᠵᠠᠯᡳᠨᡩᡝ ᠠᠰᡠᠮᠪᡳ. ᠠᡤᡝᠨᡨᡳ ᡩᠠᡳᠯᠠᠨ: https://doitong.com/mnc/developers/models/vibevoice.md
POST https://api.doitong.com/v1/run/vibevoice?wait=20
Authorization: Bearer $DOITONG_API_KEY
Content-Type: application/json
{
"script": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
"speakers": [
{
"preset": "Frank [EN]"
},
{
"preset": "Carter [EN]"
}
]
}
ᡝᡵᡝᠮᡝ ᠪᡠᠮᡝᠨᡳ ᠠᠨᠠᠮᡝ "queued" ᡳᠨᡠ "running" ᠪᡝ, GET https://api.doitong.com/v1/requests/REQUEST_ID?wait=20 ᠪᡝ ᠠᠨᠠᠮᡝ "succeeded" ᠪᡝᠴᡳ ᠠᠰᡠᠮᠪᡳ; ᡶᡳᠯᡝ ᠪᡝ outputs[].url ᠪᡝᠴᡳ ᠣᠨᡩᠣᠮᡝ. POST https://api.doitong.com/v1/quote/vibevoice ᠪᡝ ᡝᠮᡠ ᠪᡠᠶᡝᠮᡝ ᠪᡝ ᠠᠰᡠᠮᠪᡳᡩᡝ ᠵᠠᠯᡤᠠᠨ ᠪᡝ ᠶᠠᠪᡠᠮᠪᡳ ᠰᡳᠨᡳ ᠠᠮᡤᠠ ᠠᠰᡠᠮᠪᡳ ᠣᠯᡥᠣᠮᡝ.
ᡝᠨᡳ ᠵᠠᠯᡳᠨ: ≈$0.02 20 API ᠺᠷᡝᡩᡳᠲ ᡝᡵᡝ ᠵᠠᠯᡳᠨᡩᡝ ᠠᠰᡠᠮᠪᡳ
ᠰᡳᠨᡳ ᠵᠠᠮᡠᠰᡳᠨ API ᠵᡳᡵᡤᠠ. ᡝᠯᡝ ᡝᠨᡩᡝ ᡳᠯᡤᠠᠮᠪᡳ ᡝᡵᡝ ᠮᡠᠨᡩᡝ ᡴᠣᡩᡝ ᡩᠠᠮᡠ ᠮᡝᠨᡩᡝᡵᡝ ᠪᠠᡩᡝᠯᡝᠨ ᠠᠮᡪᡳ ᡳᠨᡠ API ᠵᡳᡵᡤᠠ ᡩᡝᠪᡨᡝᡵᡝ ᡩᡝ ᠠᡴᡠ᠉ ᡳᠨᡠ ᡝᡵᡝᠩᡤᡝ ᠠᠮᠪᠠᠨ ᠮᡠᠨᡩᡝ ᠪᡝ ᠠᠰᡠᡵᠠᠮᠪᡳ: ᠮᡠᡵᡝ ᡩᠠᠮᡠ ᠪᡠᠶᡝᡵᡝ ᠪᠠᡩᡝᠯᡝᠨ ᡩᡝ ᠰᡳᠨᡩᡝᠮᡝ ᠠᠪᡠᠮᡝ ᠰᠠᠮᡪᡳ᠉
ᡳᠨᡝ ᡝᠮᡠᠨᡳᠩᡤᡝ ᡝᡵᡝᠮᡝ ᡩᡝ
ᡝᡵᡝ ᠵᡠᠯᡝᠨ ᡩᡝ ᡤᡝᡪᡳᠯᡝᠨ ᠪᠠᠶᠠᠨᠠᠮᡝ ᠠᠮᡪᠠᠯᠠ ᡶᡳᠯᡝᠮᡝ ᠪᡝᠶᡝᠮᡝ᠃ API ᠵᡳᡵᡤᠠᡳ ᡤᠠᡳᡥᠠᡩᡝ ᡤᡝᡪᡳᠯᡝᠨ ᠵᠠᠯᠠᠨᠠᠮᡝ ᠪᡠᠶᡝᠮᡝ ᠮᡠᠰᡝᡳ ᠰᡠᠯᡠᠨᡩᡝ ᠪᠠᠶᠠᠨᠠᠮᡝ᠂ ᠮᡤᡳ ᠮᡠᠰᡝ ᠠᠶᠠᠨ 7 ᡥᠠᠨ ᠰᠠᡳᠨᠠᠮᡝ᠃
ᡤᡳᠰᡠᠨ ᠪᡠᠶᡝᠮᡝ
ᠵᠠᡴᡠᠨᡳ ᠵᡠᠯᡝ ᡩᡝᡵᡤᡳ ᡩᡝᠪᡝᠰᡠᠮᡝ ᠵᡠᠯᡤᡝ ᠪᡠᠶᡝᠮᡝ᠈ ᡳᠨᡳ ᡤᡳᠰᡠᠨ ᠪᠠᡳ ᡝᠨᡝᠩᡤᡳ ᠠᠮᠪᡳ
/run/vibevoice?wait=20
ᠵᠠᠯᡳᠨ → $0.02
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/vibevoice?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"script": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
"speakers": [
{
"preset": "Frank [EN]"
},
{
"preset": "Carter [EN]"
}
]
}'
# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY"
const API = "https://api.doitong.com/v1";
const headers = {
"Authorization": "Bearer " + process.env.DOITONG_API_KEY,
"Content-Type": "application/json",
};
// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/vibevoice?wait=20", {
method: "POST",
headers,
body: JSON.stringify({
"script": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
"speakers": [
{
"preset": "Frank [EN]"
},
{
"preset": "Carter [EN]"
}
]
}),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);
// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
import os
import requests
API = "https://api.doitong.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}
payload = {
"script": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
"speakers": [
{
"preset": "Frank [EN]",
},
{
"preset": "Carter [EN]",
},
],
}
# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/vibevoice", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])
# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "run",
"arguments": {
"model_id": "vibevoice",
"input": {
"script": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
"speakers": [
{
"preset": "Frank [EN]"
},
{
"preset": "Carter [EN]"
}
]
},
"wait_seconds": 20
}
}
}
ᡝᠨᡳ ᠵᠠᠯᡳᠨ ᠪᡝ ᠵᠠᠯᠠᠨᠠᠮᡝ
ᡳᠨᡝ ᠵᠠᠯᠠᠨ ᡝᡵᡝ ᠪᡠᡵᡝᠪᡝᡵᡳ ᡩᡝ ᠪᡳᠮᡝ᠈ Doitong API ᡩᡝ ᠵᡝᠯᡤᡳ ᡩᠠᡵᠠᠮᡝ᠈ Remember ᠵᡠᠯᡝᠮᡝ ᡤᡳᠯᠠᠮᡝ localStorage ᡩᡝ ᠰᡠᠯᡝᠮᡝ ᠪᡳᠮᡝ API ᠵᠠᠯᠠᠨ ᠠᠪᠠᠮᡝ
VibeVoice 1.5B ᡠᡵᡝᠮᡝ
`script` ᡳ 90000 ᠦᠰᡠ ᡩᡝ ᠠᠪᡠᡥᠠ ᠪᡝ ᠵᠠᠯᡤᠠᠨ ᡩᡝ ᠠᡠᡩᡳᠣ ᠪᡝ ᠪᡠᠮᠪᡳ。 ᠵᠠᠯᡤᠠᠨ ᠪᡝ 'Speaker X:' ᡳ ᠵᠠᠯᡤᠠᠨ ᡩᡝ ᠵᠠᠰᠠᠮᡝ᠂ `speakers` ᡳ ᠪᡳᠰᡳᡵᡝ ᠵᠠᠯᡤᠠᠨ ᠪᡝ ᠰᠣᠩᡤᠣᠮᡝ ᠪᡠᠮᠪᡳ。 `cfg_scale` 1 ᡩᡝᠨ 2 ᡩᡝᠨ ᠪᡳᠨᠠ,ᠵᠠᠯᡤᠠᠨ ᡩᡝ ᡥᡡᠯᠠᡥᠠ ᠪᡝ ᠵᠠᠯᡤᠠᠨ ᡩᡝ ᠠᠪᡠᡵᠠ ᠵᠠᠯᡤᠠᠨ ᡳ ᠵᠠᠰᠠᡥᠠᠨ ᠪᡝ ᠵᠠᠰᠠᠮᠪᡳ,`seed` ᠪᡝ ᠪᡝᡳᠯᡝᠮᡝ ᠵᠠᠰᠠᡥᠠ ᠵᠠᠰᠠᠯᠠᠨ ᠪᡝ ᠵᠠᠯᡤᠠᠨ ᡩᡝ ᠵᠠᠯᡤᠠᠨ ᡩᡝ ᠪᡠᠮᠪᡳ。 ᠠᡠᡩᡳᠣ ᠣᠴᡳ ᠮᡠᡵᡝᠨ ᠪᡝ ᠠᠪᡠᠮᡝ ᠪᡠᠮᠪᡳ。
ᠵᠠᡴᡠᠨ
scriptᡴᠠᠷᠠᡴᡡ
speakersᡴᠠᠷᠠᡴᡡ
speakers[].presetᠵᡠᠯᡝ
speakers[].audio_urlᠵᡠᠯᡝ
seedᠵᡠᠯᡝ
cfg_scaleᠵᡠᠯᡝ
enable_safety_checkerᠵᡠᠯᡝ
ᠪᡠᠶᡝᠮᡝ
{
"id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
"object": "request",
"model": "vibevoice",
"status": "succeeded",
"created_at": "2026-10-20T12:00:00Z",
"started_at": "2026-10-20T12:00:02Z",
"completed_at": "2026-10-20T12:00:09Z",
"queue_position": null,
"cost": {
"credits": 20,
"usd": "0.02",
"charged": 20,
"refunded": 0
},
"input": {
"script": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
"speakers": [
{
"preset": "Frank [EN]"
},
{
"preset": "Carter [EN]"
}
]
},
"output": {
"audio": {
"url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp3",
"content_type": "audio/mpeg",
"file_name": "0-output.mp3",
"file_size": 1843200
},
"duration": 5,
"sample_rate": 24000,
"generation_time": 5.6,
"rtf": 0.53
},
"outputs": [
{
"type": "audio",
"url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp3",
"content_type": "audio/mpeg",
"file_size": 1843200,
"duration": 12,
"stored": true
}
],
"error": null,
"metrics": {
"inference_seconds": 6.8
},
"urls": {
"self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
"cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
}
}
ᠪᡠᠶᡝᠮᡝᠨᡳ ᡤᡳᠰᡠᠨ
- audio
- object {url, content_type, file_name, file_size}ᠪᡠᠶᡝᠮᡝ ᠵᡠᠰᡝᠨ ᡳ ᡤᡳᠰᡠᠨ ᡳᠯᡳᠮᡝᠩᡤᡝ ᡶᡳᠯᡝ᠉
- duration
- numberᡤᡳᠰᡠᠨ ᡳ ᠪᡠᠶᡝᠮᡝ ᠵᠠᠯᠠᠨ᠈ ᠰᡝᡴᡠᠨ ᡩᡝ ᠵᠠᠯᠠᠨ.
- sample_rate
- integerᡤᡳᠰᡠᠨ ᡳ ᠪᡠᠶᡝᠮᡝ ᡳ ᠰᠣᠩᡤᠣᠮᠠ ᡳ ᠵᠠᠯᠠᠨ.
- generation_time
- numberᡤᡳᠰᡠᠨ ᡳ ᠪᡠᠶᡝᠮᡝ ᡳ ᠰᡝᡴᡠᠨ᠈ ᠰᡝᡴᡠᠨ ᡩᡝ ᠵᠠᠯᠠᠨ.
- rtf
- numberᠪᡠᠶᡝᠮᡝ_ᠰᡝᡴᡠᠨ ᠪᡝ ᡤᡳᠰᡠᠨ_ᠵᠠᠯᠠᠨ ᡩᡝ ᠪᡠᠯᡤᡳᠶᡝᠨ ᠣᠮᠪᡳ᠈ ᠠᠯᡳᠨ ᠵᠠᠯᡠ ᠪᡝ ᠰᠠᠩᡤᠠᠨ ᠠᡩᠠᠯᡳ.
ᡝᠯᡤᡳ Vibevoice ᡠᠯᡤᡳᠨ
ᡝᠯᡤᡳ ᡩᠠᠯᡳᠨ: ᡥᡡᠯᠠᠨ ᡩᡝ ᡤᡳᠰᡠᠨ
AI ᠠᡤᡝᠨᡨᡳ ᡠᠴᡠᠷᡳ᠈ ᡝᡵᡝ ᡩᡝᠪᡝᡵᡳ Markdown ᠰᡳᠨᡩᠠᡵᡳ https://doitong.com/mnc/developers/models/vibevoice.md. ᡝᡵᡝ ᠮᠣᡩᡝᠯ ᠵᠠᡴᡠᠨ ᠰᡠᠯᡠᠮᡝ https://doitong.com/developers/llms.txt