Text to speech

Turn a script into natural-sounding narration with ElevenLabs voices. Browse the catalog, pick a voice, and get audio you can drop straight onto a timeline.

#Generate text-to-speech audio

Enqueue a job to generate spoken-word audio from text using a selected voice.

POSThttps://api.rendley.com/v1/ai/text-to-speech

API key

Don't have one? Create an API key

Body

model_idoptionalstring

Which model to use. Changing it updates the params below.

paramsrequiredjson

Model-specific parameters. The fields listed for the selected model.

voice_idrequiredstring

Voice ID from the voice catalog.

promptrequiredstring

The exact spoken words to convert to speech audio. No stage directions or annotations.

stabilityoptionalnumber

How consistent the voice is across the clip. Higher = more monotone and stable; lower = more expressive and variable. Raise this if the voice sounds different on every generation.

similarity_boostoptionalnumber

How closely the output matches the original voice. Higher = closer to the source voice.

styleoptionalnumber

Style exaggeration of the original speaker. 0 disables style transfer. Higher values amplify the speaker's style at the cost of stability.

use_speaker_boostoptionalboolean

Boost similarity to the original speaker. Adds slight latency.

true

speedoptionalnumber

Playback speed. 1.0 is natural speed; lower is slower; higher is faster.

seedoptionalinteger

Optional seed for deterministic output. Reuse the same seed (with the same voice and settings) to get the same audio every time. Leave empty for random.

project_idoptionalstring

workspace_idoptionalstring

const res = await fetch("https://api.rendley.com/v1/ai/text-to-speech", {
  method: "POST",
  headers: { Authorization: "Bearer YOUR_API_KEY", "Content-Type": "application/json" },
  body: JSON.stringify({
    "params": {
      "voice_id": "EXAVITQu4vr4xnSDxMaL",
      "prompt": "Welcome to Rendley. Let's make something."
    },
    "model_id": "eleven-labs-tts"
  }),
});
const { data } = await res.json();

curl -X POST "https://api.rendley.com/v1/ai/text-to-speech" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "params": {
      "voice_id": "EXAVITQu4vr4xnSDxMaL",
      "prompt": "Welcome to Rendley. Let's make something."
    },
    "model_id": "eleven-labs-tts"
  }'

import requests

res = requests.post(
    "https://api.rendley.com/v1/ai/text-to-speech",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
        "params": {
            "voice_id": "EXAVITQu4vr4xnSDxMaL",
            "prompt": "Welcome to Rendley. Let's make something."
        },
        "model_id": "eleven-labs-tts"
    },
)
data = res.json()["data"]

$ch = curl_init("https://api.rendley.com/v1/ai/text-to-speech");
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_CUSTOMREQUEST, "POST");
curl_setopt($ch, CURLOPT_HTTPHEADER, ["Authorization: Bearer YOUR_API_KEY", "Content-Type: application/json"]);
curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode(["params" => ["voice_id" => "EXAVITQu4vr4xnSDxMaL", "prompt" => "Welcome to Rendley. Let's make something."], "model_id" => "eleven-labs-tts"]));

$response = curl_exec($ch);
curl_close($ch);
$data = json_decode($response, true)["data"];

package main

import (
	"fmt"
	"io"
	"net/http"
	"bytes"
)

func main() {
	body := bytes.NewBufferString(`{
  "params": {
    "voice_id": "EXAVITQu4vr4xnSDxMaL",
    "prompt": "Welcome to Rendley. Let's make something."
  },
  "model_id": "eleven-labs-tts"
}`)
	req, _ := http.NewRequest("POST", "https://api.rendley.com/v1/ai/text-to-speech", body)
	req.Header.Set("Authorization", "Bearer YOUR_API_KEY")
	req.Header.Set("Content-Type", "application/json")
	res, _ := http.DefaultClient.Do(req)
	defer res.Body.Close()
	b, _ := io.ReadAll(res.Body)
	fmt.Println(string(b))
}

require "net/http"
require "json"

uri = URI("https://api.rendley.com/v1/ai/text-to-speech")
req = Net::HTTP::Post.new(uri)
req["Authorization"] = "Bearer YOUR_API_KEY"
req["Content-Type"] = "application/json"
req.body = { params: { voice_id: "EXAVITQu4vr4xnSDxMaL", prompt: "Welcome to Rendley. Let's make something." }, model_id: "eleven-labs-tts" }.to_json

res = Net::HTTP.start(uri.hostname, uri.port, use_ssl: true) { |http| http.request(req) }
data = JSON.parse(res.body)["data"]

Response

{
  "data": {
    "job_id": "d97241f2-e1e4-4651-b078-8663fc35c584"
  }
}

#Calculate text-to-speech cost

Calculate the credit cost of generating spoken-word audio from text.

POSThttps://api.rendley.com/v1/ai/text-to-speech/cost

API key

Don't have one? Create an API key

Body

model_idoptionalstring

Which model to use. Changing it updates the params below.

paramsrequiredjson

Model-specific parameters. The fields listed for the selected model.

voice_idrequiredstring

Voice ID from the voice catalog.

promptrequiredstring

The exact spoken words to convert to speech audio. No stage directions or annotations.

stabilityoptionalnumber

How consistent the voice is across the clip. Higher = more monotone and stable; lower = more expressive and variable. Raise this if the voice sounds different on every generation.

similarity_boostoptionalnumber

How closely the output matches the original voice. Higher = closer to the source voice.

styleoptionalnumber

Style exaggeration of the original speaker. 0 disables style transfer. Higher values amplify the speaker's style at the cost of stability.

use_speaker_boostoptionalboolean

Boost similarity to the original speaker. Adds slight latency.

true

speedoptionalnumber

Playback speed. 1.0 is natural speed; lower is slower; higher is faster.

seedoptionalinteger

Optional seed for deterministic output. Reuse the same seed (with the same voice and settings) to get the same audio every time. Leave empty for random.

project_idoptionalstring

workspace_idoptionalstring

const res = await fetch("https://api.rendley.com/v1/ai/text-to-speech/cost", {
  method: "POST",
  headers: { Authorization: "Bearer YOUR_API_KEY", "Content-Type": "application/json" },
  body: JSON.stringify({
    "params": {
      "voice_id": "EXAVITQu4vr4xnSDxMaL",
      "prompt": "Welcome to Rendley. Let's make something."
    },
    "model_id": "eleven-labs-tts"
  }),
});
const { data } = await res.json();

curl -X POST "https://api.rendley.com/v1/ai/text-to-speech/cost" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "params": {
      "voice_id": "EXAVITQu4vr4xnSDxMaL",
      "prompt": "Welcome to Rendley. Let's make something."
    },
    "model_id": "eleven-labs-tts"
  }'

import requests

res = requests.post(
    "https://api.rendley.com/v1/ai/text-to-speech/cost",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
        "params": {
            "voice_id": "EXAVITQu4vr4xnSDxMaL",
            "prompt": "Welcome to Rendley. Let's make something."
        },
        "model_id": "eleven-labs-tts"
    },
)
data = res.json()["data"]

$ch = curl_init("https://api.rendley.com/v1/ai/text-to-speech/cost");
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_CUSTOMREQUEST, "POST");
curl_setopt($ch, CURLOPT_HTTPHEADER, ["Authorization: Bearer YOUR_API_KEY", "Content-Type: application/json"]);
curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode(["params" => ["voice_id" => "EXAVITQu4vr4xnSDxMaL", "prompt" => "Welcome to Rendley. Let's make something."], "model_id" => "eleven-labs-tts"]));

$response = curl_exec($ch);
curl_close($ch);
$data = json_decode($response, true)["data"];

package main

import (
	"fmt"
	"io"
	"net/http"
	"bytes"
)

func main() {
	body := bytes.NewBufferString(`{
  "params": {
    "voice_id": "EXAVITQu4vr4xnSDxMaL",
    "prompt": "Welcome to Rendley. Let's make something."
  },
  "model_id": "eleven-labs-tts"
}`)
	req, _ := http.NewRequest("POST", "https://api.rendley.com/v1/ai/text-to-speech/cost", body)
	req.Header.Set("Authorization", "Bearer YOUR_API_KEY")
	req.Header.Set("Content-Type", "application/json")
	res, _ := http.DefaultClient.Do(req)
	defer res.Body.Close()
	b, _ := io.ReadAll(res.Body)
	fmt.Println(string(b))
}

require "net/http"
require "json"

uri = URI("https://api.rendley.com/v1/ai/text-to-speech/cost")
req = Net::HTTP::Post.new(uri)
req["Authorization"] = "Bearer YOUR_API_KEY"
req["Content-Type"] = "application/json"
req.body = { params: { voice_id: "EXAVITQu4vr4xnSDxMaL", prompt: "Welcome to Rendley. Let's make something." }, model_id: "eleven-labs-tts" }.to_json

res = Net::HTTP.start(uri.hostname, uri.port, use_ssl: true) { |http| http.request(req) }
data = JSON.parse(res.body)["data"]

Response

{
  "data": 0
}

#List text-to-speech voices

List available text-to-speech voices, with optional pagination and search.

GEThttps://api.rendley.com/v1/ai/text-to-speech/voices

API key

Don't have one? Create an API key

pageoptionalstring

limitoptionalstring

queryoptionalstring

const res = await fetch("https://api.rendley.com/v1/ai/text-to-speech/voices", {
  headers: { Authorization: "Bearer YOUR_API_KEY" },
});
const { data } = await res.json();

curl "https://api.rendley.com/v1/ai/text-to-speech/voices" \
  -H "Authorization: Bearer YOUR_API_KEY"

import requests

res = requests.get(
    "https://api.rendley.com/v1/ai/text-to-speech/voices",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
)
data = res.json()["data"]

$ch = curl_init("https://api.rendley.com/v1/ai/text-to-speech/voices");
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_HTTPHEADER, ["Authorization: Bearer YOUR_API_KEY"]);

$response = curl_exec($ch);
curl_close($ch);
$data = json_decode($response, true)["data"];

package main

import (
	"fmt"
	"io"
	"net/http"
)

func main() {
	req, _ := http.NewRequest("GET", "https://api.rendley.com/v1/ai/text-to-speech/voices", nil)
	req.Header.Set("Authorization", "Bearer YOUR_API_KEY")
	res, _ := http.DefaultClient.Do(req)
	defer res.Body.Close()
	b, _ := io.ReadAll(res.Body)
	fmt.Println(string(b))
}

require "net/http"
require "json"

uri = URI("https://api.rendley.com/v1/ai/text-to-speech/voices")
req = Net::HTTP::Get.new(uri)
req["Authorization"] = "Bearer YOUR_API_KEY"

res = Net::HTTP.start(uri.hostname, uri.port, use_ssl: true) { |http| http.request(req) }
data = JSON.parse(res.body)["data"]

Response

{
  "data": [
    {
      "id": "3f0d5a4e-3d2a-4c1f-9b3e-2a1c4d5e6f70",
      "model_id": "3f0d5a4e-3d2a-4c1f-9b3e-2a1c4d5e6f70",
      "name": "string",
      "preview_audio_url": "string"
    }
  ]
}

#Get a voice preview

Get a preview audio URL for a specific text-to-speech voice.

GEThttps://api.rendley.com/v1/ai/text-to-speech/voices/{voiceId}/preview

API key

Don't have one? Create an API key

voiceIdrequiredstring

const res = await fetch("https://api.rendley.com/v1/ai/text-to-speech/voices/VOICE_ID/preview", {
  headers: { Authorization: "Bearer YOUR_API_KEY" },
});
const { data } = await res.json();

curl "https://api.rendley.com/v1/ai/text-to-speech/voices/VOICE_ID/preview" \
  -H "Authorization: Bearer YOUR_API_KEY"

import requests

res = requests.get(
    "https://api.rendley.com/v1/ai/text-to-speech/voices/VOICE_ID/preview",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
)
data = res.json()["data"]

$ch = curl_init("https://api.rendley.com/v1/ai/text-to-speech/voices/VOICE_ID/preview");
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_HTTPHEADER, ["Authorization: Bearer YOUR_API_KEY"]);

$response = curl_exec($ch);
curl_close($ch);
$data = json_decode($response, true)["data"];

package main

import (
	"fmt"
	"io"
	"net/http"
)

func main() {
	req, _ := http.NewRequest("GET", "https://api.rendley.com/v1/ai/text-to-speech/voices/VOICE_ID/preview", nil)
	req.Header.Set("Authorization", "Bearer YOUR_API_KEY")
	res, _ := http.DefaultClient.Do(req)
	defer res.Body.Close()
	b, _ := io.ReadAll(res.Body)
	fmt.Println(string(b))
}

require "net/http"
require "json"

uri = URI("https://api.rendley.com/v1/ai/text-to-speech/voices/VOICE_ID/preview")
req = Net::HTTP::Get.new(uri)
req["Authorization"] = "Bearer YOUR_API_KEY"

res = Net::HTTP.start(uri.hostname, uri.port, use_ssl: true) { |http| http.request(req) }
data = JSON.parse(res.body)["data"]

Response

{
  "data": {
    "preview_audio_url": "string"
  }
}