CSM-1B
Integrate
csm-1b
# 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/csm-1b?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"scene": [
{
"speaker_id": 0,
"text": "Hey how are you doing."
},
{
"speaker_id": 1,
"text": "Pretty good, pretty good."
},
{
"speaker_id": 0,
"text": "I'\''m great, so happy to be speaking to you."
}
]
}'
# 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 $DOITONG_API_KEY"
const API = "https://api.doitong.com/v1";
const headers = {
"Authorization": "Bearer " + process.env.DOITONG_API_KEY,
"Content-Type": "application/json",
};
// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/csm-1b?wait=20", {
method: "POST",
headers,
body: JSON.stringify({
"scene": [
{
"speaker_id": 0,
"text": "Hey how are you doing."
},
{
"speaker_id": 1,
"text": "Pretty good, pretty good."
},
{
"speaker_id": 0,
"text": "I'm great, so happy to be speaking to you."
}
]
}),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);
// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
import os
import requests
API = "https://api.doitong.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}
payload = {
"scene": [
{
"speaker_id": 0,
"text": "Hey how are you doing.",
},
{
"speaker_id": 1,
"text": "Pretty good, pretty good.",
},
{
"speaker_id": 0,
"text": "I'm great, so happy to be speaking to you.",
},
],
}
# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/csm-1b", 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/en-US/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": "csm-1b",
"input": {
"scene": [
{
"speaker_id": 0,
"text": "Hey how are you doing."
},
{
"speaker_id": 1,
"text": "Pretty good, pretty good."
},
{
"speaker_id": 0,
"text": "I'm great, so happy to be speaking to you."
}
]
}
}
Call the CSM-1B model (csm-1b) through the Doitong API. Docs for agents: https://doitong.com/en-US/developers/models/csm-1b.md
POST https://api.doitong.com/v1/run/csm-1b?wait=20
Authorization: Bearer $DOITONG_API_KEY
Content-Type: application/json
{
"scene": [
{
"speaker_id": 0,
"text": "Hey how are you doing."
},
{
"speaker_id": 1,
"text": "Pretty good, pretty good."
},
{
"speaker_id": 0,
"text": "I'm great, so happy to be speaking to you."
}
]
}
If the response status is "queued" or "running", poll GET https://api.doitong.com/v1/requests/REQUEST_ID?wait=20 until it is "succeeded"; the files are in outputs[].url. POST https://api.doitong.com/v1/quote/csm-1b with the same body returns the exact price before the run.
This request: ≈$0.03 30 API credits Run it on this page
Your new API key. It is shown only now and is already in the code and in the API key field below. Keep it secret: never put it in code that runs in a browser.
Your first result goes here
Build a request below and run it with your API key. Outputs are copied to our storage, kept forever or 7 days for free.
Build a request
Controls are generated from the model schema. The code and the price update as you change them.
/run/csm-1b?wait=20
quote → $0.03
# 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/csm-1b?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"scene": [
{
"speaker_id": 0,
"text": "Hey how are you doing."
},
{
"speaker_id": 1,
"text": "Pretty good, pretty good."
},
{
"speaker_id": 0,
"text": "I'\''m great, so happy to be speaking to you."
}
]
}'
# 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 $DOITONG_API_KEY"
const API = "https://api.doitong.com/v1";
const headers = {
"Authorization": "Bearer " + process.env.DOITONG_API_KEY,
"Content-Type": "application/json",
};
// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/csm-1b?wait=20", {
method: "POST",
headers,
body: JSON.stringify({
"scene": [
{
"speaker_id": 0,
"text": "Hey how are you doing."
},
{
"speaker_id": 1,
"text": "Pretty good, pretty good."
},
{
"speaker_id": 0,
"text": "I'm great, so happy to be speaking to you."
}
]
}),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);
// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
import os
import requests
API = "https://api.doitong.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}
payload = {
"scene": [
{
"speaker_id": 0,
"text": "Hey how are you doing.",
},
{
"speaker_id": 1,
"text": "Pretty good, pretty good.",
},
{
"speaker_id": 0,
"text": "I'm great, so happy to be speaking to you.",
},
],
}
# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/csm-1b", 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": "csm-1b",
"input": {
"scene": [
{
"speaker_id": 0,
"text": "Hey how are you doing."
},
{
"speaker_id": 1,
"text": "Pretty good, pretty good."
},
{
"speaker_id": 0,
"text": "I'm great, so happy to be speaking to you."
}
]
},
"wait_seconds": 20
}
}
}
Run this request
Your key stays in this browser: it is sent only to the Doitong API and saved (localStorage) only if you tick Remember. Get an API key
About CSM-1B
Generates speech from a required `scene`, an array of objects holding the text to speak. An optional `context` array supplies earlier conversation turns to shape delivery. The result is a single audio output. Built for dialogue-style speech.
Parameters
scenerequired
scene[].speaker_idrequired
scene[].textrequired
contextoptional
context[].promptrequired
context[].speaker_idrequired
context[].audio_urlrequired
Output
{
"id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
"object": "request",
"model": "csm-1b",
"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": 30,
"usd": "0.03",
"charged": 30,
"refunded": 0
},
"input": {
"scene": [
{
"speaker_id": 0,
"text": "Hey how are you doing."
},
{
"speaker_id": 1,
"text": "Pretty good, pretty good."
},
{
"speaker_id": 0,
"text": "I'm great, so happy to be speaking to you."
}
]
},
"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
}
},
"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"
}
}
Fields of output
- audio
- object {url, content_type, file_name, file_size} | stringAudio produced by the model.
More models: Text to Speech
For AI agents: this page as Markdown is at https://doitong.com/en-US/developers/models/csm-1b.md. All models and guides: https://doitong.com/developers/llms.txt