Text to speech

curl https://api.snapgen.org/v1/audio/speech \
  -H "Authorization: Bearer $SNAPGEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "eleven-v4",
    "input": "Welcome back! Today we explore the northern lights.",
    "voice": "JBFqnCBsd6RMkjVDRZzb",
    "response_format": "mp3"
  }' \
  --output speech.mp3

import json
import os
from urllib.request import Request, urlopen

request = Request(
    "https://api.snapgen.org/v1/audio/speech",
    data=json.dumps({
        "model": "eleven-v4",
        "input": "Welcome back! Today we explore the northern lights.",
        "voice": "JBFqnCBsd6RMkjVDRZzb",
        "response_format": "mp3",
    }).encode(),
    headers={
        "Authorization": f"Bearer {os.environ['SNAPGEN_API_KEY']}",
        "Content-Type": "application/json",
    },
)

with urlopen(request) as response, open("speech.mp3", "wb") as file:
    file.write(response.read())

import { writeFile } from "node:fs/promises";

const response = await fetch("https://api.snapgen.org/v1/audio/speech", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.SNAPGEN_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "eleven-v4",
    input: "Welcome back! Today we explore the northern lights.",
    voice: "JBFqnCBsd6RMkjVDRZzb",
    response_format: "mp3",
  }),
});
if (!response.ok) throw new Error(await response.text());
await writeFile("speech.mp3", Buffer.from(await response.arrayBuffer()));

HTTP/1.1 200 OK
content-type: audio/mpeg
cache-control: no-store
x-gateway-execution-id: 5b1e9f3a-2c4d-4e6f-8a7b-9c0d1e2f3a4b

<binary MP3 audio>

{
  "error": {
    "message": "voice: must be one of the listed voice IDs or names",
    "type": "invalid_request_error",
    "param": null,
    "code": "invalid_request"
  }
}

POST

audio

speech

curl https://api.snapgen.org/v1/audio/speech \
  -H "Authorization: Bearer $SNAPGEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "eleven-v4",
    "input": "Welcome back! Today we explore the northern lights.",
    "voice": "JBFqnCBsd6RMkjVDRZzb",
    "response_format": "mp3"
  }' \
  --output speech.mp3

import json
import os
from urllib.request import Request, urlopen

request = Request(
    "https://api.snapgen.org/v1/audio/speech",
    data=json.dumps({
        "model": "eleven-v4",
        "input": "Welcome back! Today we explore the northern lights.",
        "voice": "JBFqnCBsd6RMkjVDRZzb",
        "response_format": "mp3",
    }).encode(),
    headers={
        "Authorization": f"Bearer {os.environ['SNAPGEN_API_KEY']}",
        "Content-Type": "application/json",
    },
)

with urlopen(request) as response, open("speech.mp3", "wb") as file:
    file.write(response.read())

import { writeFile } from "node:fs/promises";

const response = await fetch("https://api.snapgen.org/v1/audio/speech", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.SNAPGEN_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "eleven-v4",
    input: "Welcome back! Today we explore the northern lights.",
    voice: "JBFqnCBsd6RMkjVDRZzb",
    response_format: "mp3",
  }),
});
if (!response.ok) throw new Error(await response.text());
await writeFile("speech.mp3", Buffer.from(await response.arrayBuffer()));

HTTP/1.1 200 OK
content-type: audio/mpeg
cache-control: no-store
x-gateway-execution-id: 5b1e9f3a-2c4d-4e6f-8a7b-9c0d1e2f3a4b

<binary MP3 audio>

{
  "error": {
    "message": "voice: must be one of the listed voice IDs or names",
    "type": "invalid_request_error",
    "param": null,
    "code": "invalid_request"
  }
}

POST /v1/audio/speech turns text into speech and returns the audio file as the response body. It accepts the OpenAI speech request (model, input, voice, response_format, and speed) and adds ElevenLabs voice settings. Choose a model from Audio Series > ElevenLabs Speech.

Model	Characters per request	Price
`eleven-v4`	Up to 10,000	$0.12 per 1,000 characters
`eleven-v3`	Up to 5,000	$0.12 per 1,000 characters
`eleven-multilingual-v2`	Up to 10,000	$0.12 per 1,000 characters
`eleven-flash-v2.5`	Up to 40,000	$0.06 per 1,000 characters

For a conversation between several voices in one file, use Text to dialogue.

string

required

One of the speech models above.

string

required

The text to speak, up to the model’s character limit. Newlines are allowed; blank text and other control characters are rejected. Each character is billed.

string

required

A voice ID or first name from the voice list, for example JBFqnCBsd6RMkjVDRZzb or George. Names are case-insensitive. OpenAI voice names such as alloy aren’t available.

string

default:"mp3"

mp3, opus, pcm, or wav. See Output formats.

number

Speaking speed, from 0.7 to 1.2.

string

An ISO 639 language code of two or three lowercase letters, such as en or de. The provider rejects a code the model doesn’t support.

number

From 0 to 1. Lower values give a broader emotional range; higher values sound more consistent from one generation to the next.

number

From 0 to 1. How closely the output follows the original voice.

number

From 0 to 1. Exaggerates the voice’s speaking style.

boolean

Boosts similarity to the original speaker.

integer

From 0 to 4294967295. Makes repeated requests more repeatable, without guaranteeing identical audio.

string

Up to 5,000 characters that come before input. Send it when you split long text across requests so the speech flows across the join. Not billed.

string

Up to 5,000 characters that follow input, for the same purpose. Not billed.

string

auto, on, or off: whether numbers, dates, and similar text are spelled out before they’re spoken.

The body is validated strictly. A field that isn’t listed here, including OpenAI’s instructions, returns invalid_request.

Response

A successful request returns HTTP 200 with the audio as the body. The gateway streams it to you as the provider sends it; save the body to a file.

Header	Value
`Content-Type`	The type of the requested `response_format`, for example `audio/mpeg`
`Cache-Control`	`no-store`
`x-gateway-execution-id`	The execution ID. Quote it when you contact support.

Output formats

`response_format`	Encoding	`Content-Type`
`mp3` (default)	MP3, 44.1 kHz, 128 kbps	`audio/mpeg`
`opus`	Opus, 48 kHz, 128 kbps	`audio/ogg`
`pcm`	Raw 16-bit PCM, 24 kHz, no header	`audio/pcm`
`wav`	WAV, 44.1 kHz	`audio/wav`

Voices

Every speech, dialogue, and voice changer model uses the same 21 ElevenLabs premade voices. Send the voice ID or the first name as voice. Other ElevenLabs voices, such as cloned or library voices, aren’t available.

Name	`voice` ID	Gender	Accent	Description	Preview
Adam	`pNInz6obpgDQGcFmaJgB`	Male	American	Dominant, Firm	Listen
Alice	`Xb7hH8MSUJpSbSDYk0k2`	Female	British	Clear, Engaging Educator	Listen
Bella	`hpp4J3VqNfWAUOO0d1Us`	Female	American	Professional, Bright, Warm	Listen
Bill	`pqHfZKP75CvOlQylNhV4`	Male	American	Wise, Mature, Balanced	Listen
Brian	`nPczCjzI2devNBz1zQrb`	Male	American	Deep, Resonant and Comforting
Callum	`N2lVS1w4EtoT3dr4eOWO`	Male	American	Husky Trickster	Listen
Charlie	`IKne3meq5aSn9XLyUdCD`	Male	Australian	Deep, Confident, Energetic
Chris	`iP95p4xoKVk53GoZ742B`	Male	American	Charming, Down-to-Earth	Listen
Daniel	`onwK4e9ZLuTAKqWW03F9`	Male	British	Steady Broadcaster
Eric	`cjVigY5qzO86Huf0OWal`	Male	American	Smooth, Trustworthy	Listen
George	`JBFqnCBsd6RMkjVDRZzb`	Male	British	Warm, Captivating Storyteller
Harry	`SOYHLrjzK2X1ezoPC6cr`	Male	American	Fierce Warrior	Listen
Jessica	`cgSgspJ2msm6clMCkdW9`	Female	American	Playful, Bright, Warm	Listen
Laura	`FGY2WhTYpPnrIDTdsKH5`	Female	American	Enthusiast, Quirky Attitude
Liam	`TX3LPaxmHKxFdv7VOQHJ`	Male	American	Energetic, Social Media Creator	Listen
Lily	`pFZP5JQG7iQjIQuC4Bku`	Female	British	Velvety Actress	Listen
Matilda	`XrExE9yKIg1WjnnlVkGX`	Female	American	Knowledgable, Professional	Listen
River	`SAz9YHcvj6GT2YYXdXww`	Neutral	American	Relaxed, Neutral, Informative	Listen
Roger	`CwhRBWXzGAHq8TQ4Fs17`	Male	American	Laid-Back, Casual, Resonant	Listen
Sarah	`EXAVITQu4vr4xnSDxMaL`	Female	American	Mature, Reassuring, Confident	Listen
Will	`bIHbv24MWmeRgasZH58o`	Male	American	Relaxed Optimist	Listen

Use the OpenAI SDK

The official OpenAI SDKs work with the SnapGen base URL. Pass a voice from the list above. In Python, send ElevenLabs fields such as stability through extra_body.

import os

from openai import OpenAI

client = OpenAI(
    api_key=os.environ["SNAPGEN_API_KEY"],
    base_url="https://api.snapgen.org/v1",
)

with client.audio.speech.with_streaming_response.create(
    model="eleven-v4",
    voice="George",
    input="Welcome back! Today we explore the northern lights.",
    response_format="mp3",
    extra_body={"stability": 0.5},
) as response:
    response.stream_to_file("speech.mp3")

const fs = require("node:fs");
const OpenAI = require("openai");

async function main() {
  const client = new OpenAI({
    apiKey: process.env.SNAPGEN_API_KEY,
    baseURL: "https://api.snapgen.org/v1",
  });

  const response = await client.audio.speech.create({
    model: "eleven-v4",
    voice: "George",
    input: "Welcome back! Today we explore the northern lights.",
    response_format: "mp3",
  });

  fs.writeFileSync("speech.mp3", Buffer.from(await response.arrayBuffer()));
}

main();

Billing

The request is billed per character of input, counted in Unicode code points: Héllo 👋 is 7 characters. previous_text and next_text are free. The gateway prices the request before it calls the provider, so the charge is known up front, and a failed request isn’t charged. For example, 1,000 characters cost $0.12 on eleven-v4 and $0.06 on eleven-flash-v2.5.

This endpoint is synchronous and rejects Idempotency-Key. If a request times out, the audio may already have been generated: check your Console request logs before you send it again.

Errors

Errors use the standard error envelope.

Status	`error.code`	Cause
400	`invalid_request`	A field is unknown or out of range, or `voice` isn’t in the voice list. The message names the field.
400	`invalid_input`	`input` is missing or empty.
400	`input_too_long`	`input` has more characters than the model accepts.
400	`invalid_content_type`	The body isn’t sent as `application/json`.
400	`idempotency_not_supported`	The request has an `Idempotency-Key` header.
400	`provider_rejected_request`	The provider refused the request, for example a `language` the model doesn’t support.
402	`insufficient_funds`	Your balance can’t cover the request.
404	`model_not_available`	The model ID is unknown or disabled. A key whose allowlist excludes the model gets `api_key_model_not_allowed` (403).
429	`rate_limit_exceeded`, `provider_rate_limited`	Too many requests. Wait for `Retry-After`, then back off.
502	`provider_http_error`, `provider_timeout`	The provider failed. Retry later.
503	`no_eligible_route`, `provider_unavailable`	The model doesn’t run on this endpoint, or no route is available right now.

curl https://api.snapgen.org/v1/audio/speech \
  -H "Authorization: Bearer $SNAPGEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "eleven-v4",
    "input": "Welcome back! Today we explore the northern lights.",
    "voice": "JBFqnCBsd6RMkjVDRZzb",
    "response_format": "mp3"
  }' \
  --output speech.mp3

import json
import os
from urllib.request import Request, urlopen

request = Request(
    "https://api.snapgen.org/v1/audio/speech",
    data=json.dumps({
        "model": "eleven-v4",
        "input": "Welcome back! Today we explore the northern lights.",
        "voice": "JBFqnCBsd6RMkjVDRZzb",
        "response_format": "mp3",
    }).encode(),
    headers={
        "Authorization": f"Bearer {os.environ['SNAPGEN_API_KEY']}",
        "Content-Type": "application/json",
    },
)

with urlopen(request) as response, open("speech.mp3", "wb") as file:
    file.write(response.read())

import { writeFile } from "node:fs/promises";

const response = await fetch("https://api.snapgen.org/v1/audio/speech", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.SNAPGEN_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "eleven-v4",
    input: "Welcome back! Today we explore the northern lights.",
    voice: "JBFqnCBsd6RMkjVDRZzb",
    response_format: "mp3",
  }),
});
if (!response.ok) throw new Error(await response.text());
await writeFile("speech.mp3", Buffer.from(await response.arrayBuffer()));

HTTP/1.1 200 OK
content-type: audio/mpeg
cache-control: no-store
x-gateway-execution-id: 5b1e9f3a-2c4d-4e6f-8a7b-9c0d1e2f3a4b

<binary MP3 audio>

{
  "error": {
    "message": "voice: must be one of the listed voice IDs or names",
    "type": "invalid_request_error",
    "param": null,
    "code": "invalid_request"
  }
}

Overview

Text Series

Image Series

Video Series

Audio Series

Endpoint Reference

Task Management

Response

Output formats

Voices

Use the OpenAI SDK

Billing

Errors

​Response

​Output formats

​Voices

​Use the OpenAI SDK

​Billing

​Errors

Response

Output formats

Voices

Use the OpenAI SDK

Billing

Errors