{
"id": "tsk_d6405d127eecb513913f7fde",
"status": "completed",
"audioUrl": "https://speakvela.com/v1/files/tsk_d6405d127eecb513913f7fde/audio.mp3?e=1793003653&s=a43833dee28c734fe275725f6f5114e504a3139520f7ad266d3fd0800ba784b8",
"audioUrlExpiresAt": "2026-10-26T08:34:13.000Z",
"durationSec": 4.99,
"characters": 79,
"modelId": "eleven_v3",
"voiceId": "auq43ws1oslv0tO4BDa7",
"voiceName": "Adam Stone - Smooth and Relaxed"
}
curl --location --request GET 'https://zylalabs.com/api/14352/expressive+text+to+speech+api/35973/text+to+speech?text=Welcome to our channel! Today we are going to talk about the history of coffee.&voiceId=auq43ws1oslv0tO4BDa7&modelId=eleven_v3&stability=0.5&similarity=0.75&speed=1&speakerBoost=true&language=en' --header 'Authorization: Bearer YOUR_API_KEY'
{
"id": "tsk_d6405d127eecb513913f7fde",
"status": "completed",
"audioUrl": "https://speakvela.com/v1/files/tsk_d6405d127eecb513913f7fde/audio.mp3?e=1793065256&s=2bb260756b2383d8f95a70336c4e38f9d82130658321d5585f08d31cd79a0ef2",
"audioUrlExpiresAt": "2026-10-27T01:40:56.000Z",
"durationSec": 4.99,
"characters": 79,
"modelId": "eleven_v3",
"voiceId": "auq43ws1oslv0tO4BDa7",
"voiceName": "Adam Stone - Smooth and Relaxed"
}
curl --location --request GET 'https://zylalabs.com/api/14352/expressive+text+to+speech+api/35974/get+speech+result&id=Required' --header 'Authorization: Bearer YOUR_API_KEY'
{
"items": [
{
"id": "Gfpl8Yo74Is0W6cPUWWT",
"name": "Max - Elearning and Documentary",
"tags": [
"professional",
"informative_educational"
],
"languages": [
{
"language": "en",
"accent": "american",
"previewUrl": "https://speakvela.com/v1/previews/a/Gfpl8Yo74Is0W6cPUWWT.mp3?payload=eyJ2b2ljZV9zb3VyY2UiOiJjdXN0b20iLCJ1c2VyX2lkIjoiQ0VaWHhmZENmRWZ5WEQ3eVVOS0lQY3VDS2FCMyIsImZpbGVuYW1lIjoiMWVkMGU2YWYtNTcxYi00YjhlLTlhYTItNzcxNWNmMjRkMDFiLm1wMyIsInRpbWVzdGFtcCI6MTc5MjQ1ODAwMDAwMDAwMH0%3D"
},
{
"language": "pt",
"accent": "brazilian",
"previewUrl": "https://speakvela.com/v1/previews/a/Gfpl8Yo74Is0W6cPUWWT.mp3?payload=eyJ2b2ljZV9zb3VyY2UiOiJjdXN0b20iLCJ1c2VyX2lkIjoiQ0VaWHhmZENmRWZ5WEQ3eVVOS0lQY3VDS2FCMyIsImZpbGVuYW1lIjoiNWExZGNkZDYtYjk5OS00MmM3LWE1ZDctN2ZkNzZlYmI1ZWQ0Lm1wMyIsInRpbWVzdGFtcCI6MTc5MjQ1ODAwMDAwMDAwMH0%3D"
},
{
"language": "el",
"accent": "el-standard",
"previewUrl": "https://speakvela.com/v1/previews/a/Gfpl8Yo74Is0W6cPUWWT.mp3?payload=eyJraW5kIjoidmVyaWZpZWRfbGFuZ3VhZ2UiLCJsYW5ndWFnZSI6ImVsIiwibW9kZWxfaWQiOiJlbGV2ZW5fbXVsdGlsaW5ndWFsX3YyIn0%3D"
},
{
"language": "hu",
"accent": "hu-standard",
"previewUrl": "https://speakvela.com/v1/previews/a/Gfpl8Yo74Is0W6cPUWWT.mp3?payload=eyJraW5kIjoidmVyaWZpZWRfbGFuZ3VhZ2UiLCJsYW5ndWFnZSI6Imh1IiwibW9kZWxfaWQiOiJlbGV2ZW5fZmxhc2hfdjJfNSJ9"
},
{
"language": "no",
"accent": "no-sørlandsk",
"previewUrl": "https://speakvela.com/v1/previews/a/Gfpl8Yo74Is0W6cPUWWT.mp3?payload=eyJraW5kIjoidmVyaWZpZWRfbGFuZ3VhZ2UiLCJsYW5ndWFnZSI6Im5vIiwibW9kZWxfaWQiOiJlbGV2ZW5fbXVsdGlsaW5ndWFsX3YyIn0%3D"
},
{
"language": "no",
"accent": "no-oslo",
"previewUrl": "https://speakvela.com/v1/previews/a/Gfpl8Yo74Is0W6cPUWWT.mp3?payload=eyJraW5kIjoidmVyaWZpZWRfbGFuZ3VhZ2UiLCJsYW5ndWFnZSI6Im5vIiwibW9kZWxfaWQiOiJlbGV2ZW5fZmxhc2hfdjJfNSJ9"
},
{
"language": "hr",
"accent": "hr-standard",
"previewUrl": "https://speakvela.com/v1/previews/a/Gfpl8Yo74Is0W6cPUWWT.mp3?payload=eyJraW5kIjoidmVyaWZpZWRfbGFuZ3VhZ2UiLCJsYW5ndWFnZSI6ImhyIiwibW9kZWxfaWQiOiJlbGV2ZW5fbXVsdGlsaW5ndWFsX3YyIn0%3D"
},
{
"language": "hr",
"accent": "hr-dubrovnik",
"previewUrl": "https://speakvela.com/v1/previews/a/Gfpl8Yo74Is0W6cPUWWT.mp3?payload=eyJraW5kIjoidmVyaWZpZWRfbGFuZ3VhZ2UiLCJsYW5ndWFnZSI6ImhyIiwibW9kZWxfaWQiOiJlbGV2ZW5fZmxhc2hfdjJfNSJ9"
},
{
"language": "hi",
"accent": "hi-standard",
"previewUrl": "https://speakvela.com/v1/previews/a/Gfpl8Yo74Is0W6cPUWWT.mp3?payload=eyJraW5kIjoidmVyaWZpZWRfbGFuZ3VhZ2UiLCJsYW5ndWFnZSI6ImhpIiwibW9kZWxfaWQiOiJlbGV2ZW5fbXVsdGlsaW5ndWFsX3YyIn0%3D"
},
{
"language": "vi",
"accent": "vi-southern",
"previewUrl": "https://speakvela.com/v1/previews/a/Gfpl8Yo74Is0W6cPUWWT.mp3?payload=eyJraW5kIjoidmVyaWZpZWRfbGFuZ3VhZ2UiLCJsYW5ndWFnZSI6InZpIiwibW9kZWxfaWQiOiJlbGV2ZW5fZmxhc2hfdjJfNSJ9"
},
{
"language": "cs",
"accent": "cs-standard",
"previewUrl": "https://speakvela.com/v1/previews/a/Gfpl8Yo74Is0W6cPUWWT.mp3?payload=eyJraW5kIjoidmVyaWZpZWRfbGFuZ3VhZ2UiLCJsYW5ndWFnZSI6ImNzIiwibW9kZWxfaWQiOiJlbGV2ZW5fZmxhc2hfdjJfNSJ9"
},
{
"language": "sv",
"accent": "sv-standard",
"previewUrl": "https://speakvela.com/v1/previews/a/Gfpl8Yo74Is0W6cPUWWT.mp3?payload=eyJraW5kIjoidmVyaWZpZWRfbGFuZ3VhZ2UiLCJsYW5ndWFnZSI6InN2IiwibW9kZWxfaWQiOiJlbGV2ZW5fdHVyYm9fdjJfNSJ9"
},
{
"language": "pl",
"accent": "pl-standard",
"previewUrl": "https://speakvela.com/v1/previews/a/Gfpl8Yo74Is0W6cPUWWT.mp3?payload=eyJraW5kIjoidmVyaWZpZWRfbGFuZ3VhZ2UiLCJsYW5ndWFnZSI6InBsIiwibW9kZWxfaWQiOiJlbGV2ZW5fbXVsdGlsaW5ndWFsX3YyIn0%3D"
},
{
"language": "ro",
"accent": "ro-standard",
"previewUrl": "https://speakvela.com/v1/previews/a/Gfpl8Yo74Is0W6cPUWWT.mp3?payload=eyJraW5kIjoidmVyaWZpZWRfbGFuZ3VhZ2UiLCJsYW5ndWFnZSI6InJvIiwibW9kZWxfaWQiOiJlbGV2ZW5fbXVsdGlsaW5ndWFsX3YyIn0%3D"
},
{
"language": "ms",
"accent": "ms-standard",
"previewUrl": "https://speakvela.com/v1/previews/a/Gfpl8Yo74Is0W6cPUWWT.mp3?payload=eyJraW5kIjoidmVyaWZpZWRfbGFuZ3VhZ2UiLCJsYW5ndWFnZSI6Im1zIiwibW9kZWxfaWQiOiJlbGV2ZW5fbXVsdGlsaW5ndWFsX3YyIn0%3D"
},
{
"language": "uk",
"accent": "other",
"previewUrl": "https://speakvela.com/v1/previews/a/Gfpl8Yo74Is0W6cPUWWT.mp3?payload=eyJraW5kIjoidmVyaWZpZWRfbGFuZ3VhZ2UiLCJsYW5ndWFnZSI6InVrIiwibW9kZWxfaWQiOiJlbGV2ZW5fZmxhc2hfdjJfNSJ9"
},
{
"language": "tr",
"accent": "tr-standard",
"previewUrl": "https://speakvela.com/v1/previews/a/Gfpl8Yo74Is0W6cPUWWT.mp3?payload=eyJraW5kIjoidmVyaWZpZWRfbGFuZ3VhZ2UiLCJsYW5ndWFnZSI6InRyIiwibW9kZWxfaWQiOiJlbGV2ZW5fbXVsdGlsaW5ndWFsX3YyIn0%3D"
},
{
"language": "ar",
"accent": "ar-modern-standard",
"previewUrl": "https://speakvela.com/v1/previews/a/Gfpl8Yo74Is0W6cPUWWT.mp3?payload=eyJraW5kIjoidmVyaWZpZWRfbGFuZ3VhZ2UiLCJsYW5ndWFnZSI6ImFyIiwibW9kZWxfaWQiOiJlbGV2ZW5fbXVsdGlsaW5ndWFsX3YyIn0%3D"
},
{
"language": "es",
"accent": "es-latin-american",
"previewUrl": "https://speakvela.com/v1/previews/a/Gfpl8Yo74Is0W6cPUWWT.mp3?payload=eyJraW5kIjoidmVyaWZpZWRfbGFuZ3VhZ2UiLCJsYW5ndWFnZSI6ImVzIiwibW9kZWxfaWQiOiJlbGV2ZW5fbXVsdGlsaW5ndWFsX3YyIn0%3D"
},
{
"language": "en",
"accent": "en-american",
"previewUrl": "https://speakvela.com/v1/previews/a/Gfpl8Yo74Is0W6cPUWWT.mp3?payload=eyJraW5kIjoidmVyaWZpZWRfbGFuZ3VhZ2UiLCJsYW5ndWFnZSI6ImVuIiwibW9kZWxfaWQiOiJlbGV2ZW5fbXVsdGlsaW5ndWFsX3YyIn0%3D"
},
{
"language": "nl",
"accent": "nl-standard",
"previewUrl": "https://speakvela.com/v1/previews/a/Gfpl8Yo74Is0W6cPUWWT.mp3?payload=eyJraW5kIjoidmVyaWZpZWRfbGFuZ3VhZ2UiLCJsYW5ndWFnZSI6Im5sIiwibW9kZWxfaWQiOiJlbGV2ZW5fbXVsdGlsaW5ndWFsX3YyIn0%3D"
},
{
"language": "de",
"accent": "other",
"previewUrl": "https://speakvela.com/v1/previews/a/Gfpl8Yo74Is0W6cPUWWT.mp3?payload=eyJraW5kIjoidmVyaWZpZWRfbGFuZ3VhZ2UiLCJsYW5ndWFnZSI6ImRlIiwibW9kZWxfaWQiOiJlbGV2ZW5fbXVsdGlsaW5ndWFsX3YyIn0%3D"
},
{
"language": "de",
"accent": "de-standard",
"previewUrl": "https://speakvela.com/v1/previews/a/Gfpl8Yo74Is0W6cPUWWT.mp3?payload=eyJraW5kIjoidmVyaWZpZWRfbGFuZ3VhZ2UiLCJsYW5ndWFnZSI6ImRlIiwibW9kZWxfaWQiOiJlbGV2ZW5fZmxhc2hfdjJfNSJ9"
},
{
"language": "pt",
"accent": "pt-brazilian",
"previewUrl": "https://speakvela.com/v1/previews/a/Gfpl8Yo74Is0W6cPUWWT.mp3?payload=eyJraW5kIjoidmVyaWZpZWRfbGFuZ3VhZ2UiLCJsYW5ndWFnZSI6InB0IiwibW9kZWxfaWQiOiJlbGV2ZW5fZmxhc2hfdjJfNSJ9"
}
],
"quality": "high",
"description": "A friendly, articulate eLearning voice, great for teaching, documentaries, and explainers",
"previewUrl": "https://speakvela.com/v1/previews/a/Gfpl8Yo74Is0W6cPUWWT.mp3?payload=eyJ2b2ljZV9zb3VyY2UiOiJjdXN0b20iLCJ1c2VyX2lkIjoiQ0VaWHhmZENmRWZ5WEQ3eVVOS0lQY3VDS2FCMyIsImZpbGVuYW1lIjoiMWVkMGU2YWYtNTcxYi00YjhlLTlhYTItNzcxNWNmMjRkMDFiLm1wMyIsInRpbWVzdGFtcCI6MTc5MjQ1ODAwMDAwMDAwMH0%3D",
"gender": "male",
"age": "middle_aged",
"language": "en",
"accent": "american",
"useCase": "informative_educational",
"category": "informative_educational"
},
{
"id": "7b9mYhmnp0y2qSH1FnBL",
"name": "Bunty - Funny Best Friend",
"tags": [
"upbeat",
"characters_animation"
],
"languages": [
{
"language": "hi",
"accent": "standard",
"previewUrl": "https://speakvela.com/v1/previews/g/ZGF0YWJhc2Uvd29ya3NwYWNlL2VkOWIwNWU2MzI0YzQ1NzY4NTQ5MDM1MmU5YTFlYzkwL3ZvaWNlcy83YjltWWhtbnAweTJxU0gxRm5CTC9wM1RINkNJT2lSNmRGMkJYUW10dy5tcDM.mp3"
},
{
"language": "hr",
"accent": "hr-dubrovnik"
}
]
}
],
"_note": "Response truncated for documentation purposes"
}
curl --location --request GET 'https://zylalabs.com/api/14352/expressive+text+to+speech+api/35975/search+voices?pageSize=3' --header 'Authorization: Bearer YOUR_API_KEY'
{
"status": "completed",
"audioUrl": "https://speakvela.com/v1/files/merge/mrg_e10b25a34bb6acb57b011fb9.mp3?e=1793067601&s=14ff857fe9b70bca04dcb8642c28e2bd4d56bb0bb420a87ba16a1e211c533607",
"audioUrlExpiresAt": "2026-10-27T02:20:01.000Z",
"parts": 2,
"durationSec": 11.21
}
curl --location --request GET 'https://zylalabs.com/api/14352/expressive+text+to+speech+api/35976/merge+speech+parts?ids=tsk_d6405d127eecb513913f7fde,tsk_c58203a8821203f352e3f194' --header 'Authorization: Bearer YOUR_API_KEY'
After signing up, every developer is assigned a personal API access key, a unique combination of letters and digits provided to access to our API endpoint. To authenticate with the Expressive Text to Speech API simply include your bearer token in the Authorization header.
| Header | Description |
|---|---|
Authorization
|
Required
Should be Bearer access_key. See "Your API Access Key" above when you are subscribed.
|
No long-term commitment. Upgrade, downgrade, or cancel anytime. Free Trial includes up to 50 requests.
Convert up to 1,000 characters of text into expressive, emotional speech in one call and get an MP3 download link. v3, v4 and v4 Turbo voice models, many languages.
Call Text to Speech with the text, a voice id and a model id. The request waits until the audio is ready, usually 10 to 40 seconds, and returns a link to the finished MP3 file.
Up to 1,000 characters per call. For a longer text, convert it in parts of up to 1,000 characters, then pass the ids of the parts in reading order to Merge Speech Parts. You get one MP3 that joins all parts with a short pause between them, up to 250 parts.
Any public voice from the voice library. Use Search Voices to find voices by name, language, gender, age or accent, then pass the voice id as voiceId. Cloned and private voices are not supported.
Every language the chosen model supports. The language is detected from the text, or you can set it with the language parameter using an ISO 639-1 code such as en, es or de.
The audioUrl works for 7 days and needs no API key, so you can give it directly to a browser, an audio player or another service. Download the file if you need to keep it longer.
The audio was not ready within about 50 seconds. The response has an id: call Get Speech Result with that id a few seconds later to get the same response with the MP3 link.
Errors such as a text over 1,000 characters, an unknown voice or a refused text return an error code instead of 200, and you can fix the request and send it again.
V3, v4 and v4 Turbo, with the model ids eleven_v3, eleven_v4 and eleven_v4_turbo. Multilingual v2, Flash v2.5 and Turbo v2.5 are in our separate "Multilingual Text to Speech API".
Each endpoint returns JSON data. The Text to Speech endpoint provides an audio URL, job status, duration, character count, model ID, and voice ID. The Get Speech Result endpoint returns similar data for a specific speech job. The Search Voices endpoint returns a list of available voices with details like name, tags, languages, and preview URLs. The Merge Speech Parts endpoint returns a combined audio URL and metadata about the merged parts.
Key fields include `id` (job identifier), `status` (job completion status), `audioUrl` (link to the MP3 file), `audioUrlExpiresAt` (expiration time of the link), `durationSec` (length of the audio), `characters` (number of characters processed), `modelId` (used voice model), and `voiceId` (specific voice used). These fields help users track and utilize the generated audio effectively.
The Text to Speech endpoint requires parameters like `text` (the input text), `voiceId` (selected voice), and `modelId` (voice model). The Search Voices endpoint allows filtering by `name`, `language`, `gender`, `age`, and `accent`. The Merge Speech Parts endpoint requires a list of `audioIds` to specify the order of MP3 files to merge. Users can customize requests based on their needs.
The response data is structured in JSON format, with key-value pairs for easy access. For example, the Text to Speech response includes fields like `id`, `status`, and `audioUrl` at the top level. This organization allows users to quickly identify and utilize the information they need, such as accessing the audio file or checking the job status.
Typical use cases include creating audio content for e-learning, generating voiceovers for videos, and developing interactive applications that require speech output. Users can also merge multiple audio segments for longer texts, making it suitable for audiobooks or presentations. The expressive speech capabilities enhance user engagement in various applications.
Users can utilize the returned data by accessing the `audioUrl` to download or stream the generated speech. The `status` field helps track job completion, while `durationSec` informs users about the length of the audio. For merged audio, the `parts` field indicates how many segments were combined, allowing users to manage their audio files efficiently.
The Text to Speech endpoint provides audio generation results, including audio links and job status. The Get Speech Result endpoint offers detailed information about a specific speech job. The Search Voices endpoint lists available voices with attributes like language and accent. The Merge Speech Parts endpoint gives details about the merged audio, including its duration and number of parts.
Data accuracy is maintained through the use of advanced voice models (v3, v4, v4 Turbo) that are regularly updated and trained on diverse datasets. The API ensures that the voices produced are expressive and emotional, enhancing the quality of the generated speech. Continuous improvements and user feedback also contribute to maintaining high standards in voice synthesis.
To obtain your API key, first sign in to your account and navigate to the API you want to use. From the API's Pricing section, choose a plan and complete the subscription process. Once subscribed, return to the API page and you will see your API Access Key displayed at the top of the documentation page. You can use this key to authenticate your requests.
You can’t switch APIs during the free trial. If you subscribe to a different API, your trial will end and the new subscription will start as a paid plan.
The free trial lasts for 7 days and allows you to make up to 50 API requests.
No, the free trial is available only once, so we recommend using it on the API that interests you the most. Most of our APIs offer a free trial, but some may not include this option.
Yes. If the API offers a free trial, you will see a "Free 7-Day Trial" option in its Pricing section. The trial lasts for 7 days and allows up to 50 API requests, enabling you to evaluate the API before subscribing to a paid plan.
Zyla API Hub is like a big store for APIs, where you can find thousands of them all in one place. We also offer dedicated support and real-time monitoring of all APIs. Once you sign up, you can pick and choose which APIs you want to use. Just remember, each API needs its own subscription. But if you subscribe to multiple ones, you'll use the same key for all of them, making things easier for you.
You can monitor your API usage through the response headers included with every request:
x-zyla-api-calls-monthly-used: Shows the total number of API requests you have used during the current billing period.
x-zyla-api-calls-monthly-remaining: Shows the number of API requests you have remaining for the current billing period.
Yes, you can cancel your subscription at any time. Simply go to the Pricing section of the API you're subscribed to and click the "Unsubscribe" button.
Please note that upgrades, downgrades, and cancellations take effect immediately. Once your subscription is canceled, access to the service will end immediately, regardless of any remaining API calls in your quota.
Please have a look at our Refund Policy: https://zylalabs.com/terms#refund