curl --location 'https://api.zerogpu.ai/v1/audio/speech' \
--header 'content-type: application/json' \
--header 'x-api-key: YOUR_API_KEY' \
--data '{
"model": "chatterbox",
"input": "[dramatic] Oh, another AI model that needs eight GPUs just to say hello? [sarcastic] How adorable. [shush] Do not tell anyone... [happy] I run on the edge.",
"voice": "default",
"response_format": "mp3",
"seed": 42,
"temperature": 0.8,
"top_p": 0.95,
"repetition_penalty": 1.2
}' \
--output speech.mp3
curl --location 'https://api.zerogpu.ai/v1/audio/speech' \
--header 'x-api-key: YOUR_API_KEY' \
--form 'model="chatterbox"' \
--form 'input="Testing model to generate voice. Hey how are you today?"' \
--form 'response_format="mp3"' \
--form 'seed="42"' \
--form 'voice_sample=@"/path/to/file"' \
--output speech.mp3
from openai import OpenAI
client = OpenAI(
base_url="https://api.zerogpu.ai/v1",
api_key="YOUR_API_KEY", # sent as Authorization: Bearer
)
with client.audio.speech.with_streaming_response.create(
model="chatterbox",
voice="alloy", # OpenAI voice names map to the built-in voice
input="Hello from ZeroGPU.",
response_format="mp3",
) as response:
response.stream_to_file("speech.mp3")
import fs from "node:fs";
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.zerogpu.ai/v1",
apiKey: "YOUR_API_KEY", // sent as Authorization: Bearer
});
const speech = await client.audio.speech.create({
model: "chatterbox",
voice: "alloy", // OpenAI voice names map to the built-in voice
input: "Hello from ZeroGPU.",
response_format: "mp3",
});
fs.writeFileSync("speech.mp3", Buffer.from(await speech.arrayBuffer()));
"<string>"{
"error": {
"message": "'input' is required",
"type": "invalid_request_error",
"param": "input",
"code": "input_required"
}
}{
"error": {
"message": "You exceeded your current quota, please check your plan and billing details.",
"type": "insufficient_quota",
"param": null,
"code": "insufficient_quota"
}
}By model
chatterbox
Model details for chatterbox. The original 0.5B ChatterboxTTS, with zero-shot voice cloning.
POST
/
audio
/
speech
curl --location 'https://api.zerogpu.ai/v1/audio/speech' \
--header 'content-type: application/json' \
--header 'x-api-key: YOUR_API_KEY' \
--data '{
"model": "chatterbox",
"input": "[dramatic] Oh, another AI model that needs eight GPUs just to say hello? [sarcastic] How adorable. [shush] Do not tell anyone... [happy] I run on the edge.",
"voice": "default",
"response_format": "mp3",
"seed": 42,
"temperature": 0.8,
"top_p": 0.95,
"repetition_penalty": 1.2
}' \
--output speech.mp3
curl --location 'https://api.zerogpu.ai/v1/audio/speech' \
--header 'x-api-key: YOUR_API_KEY' \
--form 'model="chatterbox"' \
--form 'input="Testing model to generate voice. Hey how are you today?"' \
--form 'response_format="mp3"' \
--form 'seed="42"' \
--form 'voice_sample=@"/path/to/file"' \
--output speech.mp3
from openai import OpenAI
client = OpenAI(
base_url="https://api.zerogpu.ai/v1",
api_key="YOUR_API_KEY", # sent as Authorization: Bearer
)
with client.audio.speech.with_streaming_response.create(
model="chatterbox",
voice="alloy", # OpenAI voice names map to the built-in voice
input="Hello from ZeroGPU.",
response_format="mp3",
) as response:
response.stream_to_file("speech.mp3")
import fs from "node:fs";
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.zerogpu.ai/v1",
apiKey: "YOUR_API_KEY", // sent as Authorization: Bearer
});
const speech = await client.audio.speech.create({
model: "chatterbox",
voice: "alloy", // OpenAI voice names map to the built-in voice
input: "Hello from ZeroGPU.",
response_format: "mp3",
});
fs.writeFileSync("speech.mp3", Buffer.from(await speech.arrayBuffer()));
"<string>"{
"error": {
"message": "'input' is required",
"type": "invalid_request_error",
"param": "input",
"code": "input_required"
}
}{
"error": {
"message": "You exceeded your current quota, please check your plan and billing details.",
"type": "insufficient_quota",
"param": null,
"code": "insufficient_quota"
}
}This model is routable only on
/v1/audio/speech. To clone a voice, send
multipart/form-data with a voice_sample file.Resemble AI’s Chatterbox is the original 0.5B-parameter ChatterboxTTS model, the larger sibling of chatterbox-nano. It speaks your text in a built-in voice, or clones a speaker zero-shot from a short reference clip you upload with the request, and inline tags such asReferences: Model card • License • Terms • Privacy[dramatic],[sarcastic], and[happy]steer delivery. It runs on the samePOST /v1/audio/speechendpoint, and its generated audio is billed per second, rounded up to the next whole second per request, rather than per whole minute.
Limits
| Limit | Value |
|---|---|
input length | 2,000 characters. Requests near the limit can time out with 524. |
voice_sample duration | 6 to 30 seconds |
voice_sample size | 10 MB |
voice_sample formats | mp3, m4a, wav, flac, ogg, webm, mp4 |
curl --location 'https://api.zerogpu.ai/v1/audio/speech' \
--header 'content-type: application/json' \
--header 'x-api-key: YOUR_API_KEY' \
--data '{
"model": "chatterbox",
"input": "[dramatic] Oh, another AI model that needs eight GPUs just to say hello? [sarcastic] How adorable. [shush] Do not tell anyone... [happy] I run on the edge.",
"voice": "default",
"response_format": "mp3",
"seed": 42,
"temperature": 0.8,
"top_p": 0.95,
"repetition_penalty": 1.2
}' \
--output speech.mp3
curl --location 'https://api.zerogpu.ai/v1/audio/speech' \
--header 'x-api-key: YOUR_API_KEY' \
--form 'model="chatterbox"' \
--form 'input="Testing model to generate voice. Hey how are you today?"' \
--form 'response_format="mp3"' \
--form 'seed="42"' \
--form 'voice_sample=@"/path/to/file"' \
--output speech.mp3
from openai import OpenAI
client = OpenAI(
base_url="https://api.zerogpu.ai/v1",
api_key="YOUR_API_KEY", # sent as Authorization: Bearer
)
with client.audio.speech.with_streaming_response.create(
model="chatterbox",
voice="alloy", # OpenAI voice names map to the built-in voice
input="Hello from ZeroGPU.",
response_format="mp3",
) as response:
response.stream_to_file("speech.mp3")
import fs from "node:fs";
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.zerogpu.ai/v1",
apiKey: "YOUR_API_KEY", // sent as Authorization: Bearer
});
const speech = await client.audio.speech.create({
model: "chatterbox",
voice: "alloy", // OpenAI voice names map to the built-in voice
input: "Hello from ZeroGPU.",
response_format: "mp3",
});
fs.writeFileSync("speech.mp3", Buffer.from(await speech.arrayBuffer()));
Body
multipart/form-dataapplication/json
Multipart form, required for voice cloning.
Response
The audio file, with a content type matching response_format.
The response is of type file.

