Welcome to our API documentation! With Monster API, you can effortlessly access powerful generative AI models such as stable diffusion for text to image and image to image, with our auto-scaling APIs, zero management required.
\nHere we will walk you through the process of using our APIs for accessing state-of-the-art AI models such as Stable Diffusion, Dreambooth, Open AI Whisper (coming soon) at scale.
\nAPI Base URL:
\nhttps://api.monsterapi.ai
Security Headers:
\nx-api-key: 123Authorization: Bearer 123Generate an API Key and Auth token on Monster API Website.
\nAdditional Information:
\nReach out to us for any query or view our terms of service here:
\n\n\nAll the AI models are executed asynchronously on Monster API.
\n
Text to image API allows you to generate an image that looks similar to your provided textual instruction (prompt) using Stable Diffusion v1.5 model.
\nText to Image model requires a text prompt as an input to render images that are conditioned on your provided text prompt.
\nYou may further optimise the quality of output images by passing additional parameters like:
\nMonsterAPI Text to Image API is highly optimised and costs as low as $5* for 1000 image generations.
\n\n\n* Pricing varies on factors like the processing time, sampling steps and other request parameters.
\n
We assume that you have your x-api-key and Auth Token handy. If you do not have one already, then follow these steps first:
\nheaders = {\n 'x-api-key': '123',\n 'Authorization': 'Bearer 456'\n}\n\nThis REST API works asynchronously and accepts the requests received from send-request API, for which the request status can be viewed using fetch-status API.
\nThis collection shows 2 examples on how to send request and fetch the request status for stable diffusion v1.5 model execution.
\n\"model\": \"txt2img\",\n\"data\": {\n \"prompt\": \"\",\n \"negprompt\": \"\",\n \"samples\": 1,\n \"steps\": 50,\n \"aspect_ratio\": \"square\",\n \"guidance_scale\": 12.5,\n \"seed\": 2321\n }\n\nThe parameters passed in data list are described below:
2. Example body for Text to Image Fetch Request Status:
\n\"process_id\" : \"\"\n\nThe parameters passed in above API request are described below:
\n","urlObject":{"query":[],"variable":[]}},"response":[{"id":"bf5de16a-ae04-4a9c-9901-b40b8eb0ee01","name":"Send request","originalRequest":{"method":"POST","header":[{"key":"Authorization","value":"Bearer 456"},{"key":"Content-Type","value":"application/json"}],"body":{"mode":"raw","raw":"{\n \"model\": \"txt2img\",\n \"data\": {\n \"prompt\" : \"highly detailed photo of Cute face of Lionel Messi, 3 year old, unreal engine, cinematic lighting, 8K, dark background, face in focus, (by Alyssa Monks:1.1), by Joseph Lorusso, by Lilia Alvarado\",\n \"negprompt\": \"lowres, signs, memes, labels, text, food, text, error, mutant, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, made by children, caricature, ugly, boring, sketch, lacklustre, repetitive, cropped, (long neck), facebook, youtube, body horror, out of frame, mutilated, tiled, frame, border, porcelain skin, doll like, doll, bad quality, cartoon, lowres, meme, low quality, worst quality, ugly, disfigured, inhuman\",\n \"samples\" : 1,\n \"steps\" : 50,\n \"aspect_ratio\" : \"square\",\n \"guidance_scale\": 12.5,\n \"seed\": 2321\n }\n}","options":{"raw":{"language":"json"}}},"url":"https://api.monsterapi.ai/apis/add-task"},"_postman_previewlanguage":"json","header":null,"cookie":[],"responseTime":null,"body":"{\n \"message\": \"Request accepted successfully\",\n \"process_id\": \"058c604c-aacb-11ed-a970-d78ebbbbe581\"\n}"},{"id":"4ff8d7f6-74f6-4e2e-951c-a7579a2ba0bf","name":"Fetch request status","originalRequest":{"method":"POST","header":[{"key":"Authorization","value":"Bearer 456"}],"body":{"mode":"raw","raw":"{\n \"process_id\" : \"058c604c-aacb-11ed-a970-d78ebbbbe581\"\n}","options":{"raw":{"language":"json"}}},"url":"https://api.monsterapi.ai/apis/task-status"},"_postman_previewlanguage":"json","header":null,"cookie":[],"responseTime":null,"body":"{\n \"message\": \"Request processed successfully\",\n \"response_data\": {\n \"process_id\": \"058c604c-aacb-11ed-a970-d78ebbbbe581\",\n \"status\": \"COMPLETED\",\n \"result\": {\n \"output\": [\n \"https://processed-model-result.s3.us-east-2.amazonaws.com/058c604c-aacb-11ed-a970-d78ebbbbe581_0.png\"\n ]\n },\n \"credit_used\": 5,\n \"overage\": 0\n }\n}"}],"_postman_id":"03b0fb36-ba8d-4ebf-b6e6-24e9ce4e4e55"},{"name":"Text to Image - SDXL","id":"37336bc8-7a4b-41fe-b253-6a6f7ba63c82","protocolProfileBehavior":{"disableBodyPruning":true},"request":{"auth":{"type":"noauth","isInherited":false},"method":"POST","header":[{"key":"Authorization","value":"Bearer 456"}],"body":{"mode":"raw","raw":"","options":{"raw":{"language":"json"}}},"url":"","description":"\n\nAll the AI models are executed asynchronously on Monster API.
\n
Text to image SD XL API allows you to generate an image that looks similar to your provided text prompt using Stable Diffusion XL model.
\nText to Image Stable Diffusion XL model requires a text prompt as an input to render images that are conditioned on your provided text prompt.
\nYou may further optimise the quality of output images by passing additional parameters like:
\nMonsterAPI Text to Image API is highly optimised and costs as low as $8* for 1000 image generations.
\n\n\n* Pricing varies on factors like the processing time, sampling steps and other request parameters.
\n
We assume that you have your x-api-key and Auth Token handy. If you do not have one already, then follow these steps first:
\nheaders = {\n 'x-api-key': '123',\n 'Authorization': 'Bearer 456'\n}\n\nThis REST API works asynchronously and accepts the requests received from send-request API, for which the request status can be viewed using fetch-status API.
\nThis collection shows 2 examples on how to send request and fetch the request status for sdxl-base model execution.
\n\"model\": \"sdxl-base\",\n\"data\": {\n \"prompt\": \"\",\n \"negprompt\": \"\",\n \"samples\": 1,\n \"steps\": 50,\n \"aspect_ratio\": \"square\",\n \"guidance_scale\": 12.5,\n \"seed\": 2321\n }\n\nThe parameters passed in data list are described below:
2. Example body for Text to Image SDXL Fetch Request Status:
\n\"process_id\" : \"\"\n\nThe parameters passed in above API request are described below:
\n","urlObject":{"query":[],"variable":[]}},"response":[{"id":"3319c169-f325-4bed-8b05-b820d12d71bc","name":"Send request","originalRequest":{"method":"POST","header":[{"key":"Authorization","value":"Bearer 456"},{"key":"Content-Type","value":"application/json"}],"body":{"mode":"raw","raw":"{\n \"model\": \"sdxl-base\",\n \"data\": {\n \"prompt\" : \"Photo of an astronaut riding a llama on Mars\",\n \"negprompt\": \"lowres, signs, memes, labels, text, food, text, error, mutant, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, made by children, caricature, ugly, boring, sketch, lacklustre, repetitive, cropped, (long neck), facebook, youtube, body horror, out of frame, mutilated, tiled, frame, border, porcelain skin, doll like, doll, bad quality, cartoon, lowres, meme, low quality, worst quality, ugly, disfigured, inhuman\",\n \"samples\" : 1,\n \"steps\" : 50,\n \"aspect_ratio\" : \"square\",\n \"guidance_scale\": 12.5,\n \"seed\": 2321\n }\n}","options":{"raw":{"language":"json"}}},"url":"https://api.monsterapi.ai/apis/add-task"},"_postman_previewlanguage":"json","header":null,"cookie":[],"responseTime":null,"body":"{\n \"message\": \"Request accepted successfully\",\n \"process_id\": \"093212f3-3209-11ee-9434-af0e00a0e85c\"\n}"},{"id":"38e97eb6-5273-4843-9f15-7be604b15130","name":"Fetch request status","originalRequest":{"method":"POST","header":[{"key":"Authorization","value":"Bearer 456"}],"body":{"mode":"raw","raw":"{\n \"process_id\" : \"093212f3-3209-11ee-9434-af0e00a0e85c\"\n}","options":{"raw":{"language":"json"}}},"url":"https://api.monsterapi.ai/apis/task-status"},"_postman_previewlanguage":"json","header":null,"cookie":[],"responseTime":null,"body":"{\n \"message\": \"Request processed successfully\",\n \"response_data\": {\n \"process_id\": \"093212f3-3209-11ee-9434-af0e00a0e85c\",\n \"status\": \"COMPLETED\",\n \"result\": {\n \"output\": [\n \"https://processed-model-result.s3.us-east-2.amazonaws.com/093212f3-3209-11ee-9434-af0e00a0e85c_0.png\"\n ]\n },\n \"credit_used\": 8,\n \"overage\": 0\n }\n}"}],"_postman_id":"37336bc8-7a4b-41fe-b253-6a6f7ba63c82"},{"name":"Image to Image","id":"5af3aaa8-5ddf-4774-9066-78fd61ee628f","protocolProfileBehavior":{"disableBodyPruning":true},"request":{"auth":{"type":"noauth","isInherited":false},"method":"POST","header":[{"key":"Authorization","value":"Bearer 456"}],"body":{"mode":"raw","raw":"","options":{"raw":{"language":"json"}}},"url":"","description":"\n\nAll the AI models are executed asynchronously on Monster API.
\n
Image to image API allows you to generate that resembles an original image provided by you, using stable diffusion model.
\nImage to Image model requires a text prompt and an initial image url as the inputs to render a new image which has similar style and content to the initial image, but different details and composition.
\nMonsterAPI Image to Image API is highly optimised and costs as low as $5* for 1000 image generations.
\n\n\n* Pricing varies on factors like the processing time, sampling steps and other request parameters.
\n
We assume that you have your x-api-key and Auth Token handy. If you do not have one already, then follow these steps first:
\nheaders = {\n 'x-api-key': '123',\n 'Authorization': 'Bearer 456'\n}\n\nThis collection shows 2 examples on how to send request and fetch the request status.
\n\"model\": \"img2img\",\n\"data\": {\n \"prompt\": \"\",\n \"negprompt\": \"\",\n \"steps\": 50,\n \"init_image_url\": \"\",\n \"strength\": \"\",\n \"guidance_scale\": 12.5,\n \"seed\": 2321\n }\n\nThe parameters passed in data list are described below:
2. Example body for Image to Image Fetch Request Status:
\n\"process_id\" : \"\"\n\nThe parameters passed in above API request are described below:
\n","urlObject":{"query":[],"variable":[]}},"response":[{"id":"00c24012-e889-42b8-9710-90ee45485a72","name":"Send request","originalRequest":{"method":"POST","header":[{"key":"Authorization","value":"Bearer 456"},{"key":"Content-Type","value":"application/json"}],"body":{"mode":"raw","raw":"{\n \"model\": \"img2img\",\n \"data\": {\n \"prompt\" : \"A fantasy landscape, beautiful, photorealistic, trending on artstation\",\n \"negprompt\": \"\",\n \"steps\" : 50,\n \"guidance_scale\": 12.5,\n \"init_image_url\": \"https://i.pinimg.com/originals/1c/31/8e/1c318ed6a76b5c1573f0f816516beea3.jpg\",\n \"strength\": 0.75,\n \"seed\": 2321\n }\n}","options":{"raw":{"language":"json"}}},"url":"https://api.monsterapi.ai/apis/add-task"},"_postman_previewlanguage":"json","header":null,"cookie":[],"responseTime":null,"body":"{\n \"message\": \"Request accepted successfully\",\n \"process_id\": \"6699be46-aad0-11ed-a45e-b161ab1b7fd3\"\n}"},{"id":"a65d6639-32b5-4fa0-adf0-71ca2e4b7e2e","name":"Fetch request status","originalRequest":{"method":"POST","header":[{"key":"Authorization","value":"Bearer 456"}],"body":{"mode":"raw","raw":"{\n \"process_id\" : \"6699be46-aad0-11ed-a45e-b161ab1b7fd3\"\n}","options":{"raw":{"language":"json"}}},"url":"https://api.monsterapi.ai/apis/task-status"},"_postman_previewlanguage":"json","header":null,"cookie":[],"responseTime":null,"body":"{\n \"message\": \"Request processed successfully\",\n \"response_data\": {\n \"process_id\": \"6699be46-aad0-11ed-a45e-b161ab1b7fd3\",\n \"status\": \"COMPLETED\",\n \"result\": {\n \"output\": [\n \"https://processed-model-result.s3.us-east-2.amazonaws.com/6699be46-aad0-11ed-a45e-b161ab1b7fd3_0.png\"\n ]\n },\n \"credit_used\": 6,\n \"overage\": 0\n }\n}"}],"_postman_id":"5af3aaa8-5ddf-4774-9066-78fd61ee628f"},{"name":"Instruct-pix2pix","id":"3fcbe73c-52ea-4d42-8f6d-521519021d95","protocolProfileBehavior":{"disableBodyPruning":true},"request":{"auth":{"type":"noauth","isInherited":false},"method":"POST","header":[{"key":"Authorization","value":"Bearer 456"}],"body":{"mode":"raw","raw":"","options":{"raw":{"language":"json"}}},"url":"","description":"\n\nAll the AI models are executed asynchronously on Monster API.
\n
Pix2Pix API allows you to edit any image by using simple text instructions. This API uses Instruct-pix2pix model made by Timothy Brooks.
\nPix2Pix model requires a text prompt and an initial image url as the inputs to render a new image which has similar style and content to the initial image, but different details and composition.
\nThe following file formats are supported: jpg, jpeg, png
You may further optimise the outputs by passing additional parameters like:
\nMonsterAPI Pix2Pix API is highly optimised and costs as low as $5* for 1000 image edits.
\n\n\n* Pricing varies on factors like the processing time and parameters passed.
\n
We assume that you have your x-api-key and Auth Token handy. If you do not have one already, then follow these steps first:
\nheaders = {\n 'x-api-key': '123',\n 'Authorization': 'Bearer 456'\n}\n\nThis REST API works asynchronously and accepts the requests received from send-request API, for which the request status can be viewed using fetch-status API.
\nThis collection shows 2 examples on how to send request and fetch the request status for instruct-pix2pix model execution.
\n\"model\": \"pix2pix\",\n\"data\": {\n \"prompt\" : \"\",\n \"negprompt\": \"\",\n \"steps\" : 50,\n \"init_image_url\": \"\",\n \"guidance_scale\": 12.5,\n \"image_guidance_scale\": 1.5,\n \"seed\": 29123\n}\n\nThe parameters passed in data list are described below:
2. Example body for Image to Image Fetch Request Status:
\n\"process_id\" : \"\"\n\nThe parameters passed in above API request are described below:
\n","urlObject":{"query":[],"variable":[]}},"response":[{"id":"39df4ef7-ad5a-4984-ba9a-4f7babf0c7c2","name":"Send request","originalRequest":{"method":"POST","header":[{"key":"Authorization","value":"Bearer 456"},{"key":"Content-Type","value":"application/json"}],"body":{"mode":"raw","raw":"{\n \"model\": \"pix2pix\",\n \"data\": {\n \"prompt\" : \"Add mountains in background\",\n \"negprompt\": \"\",\n \"steps\" : 50,\n \"guidance_scale\": 12.5,\n \"init_image_url\": \"https://img.freepik.com/free-photo/young-curly-man-with-thumbs-up-isolated-blue-wall_231208-1245.jpg\",\n \"image_guidance_scale\": 1.5,\n \"seed\": 29123\n }\n}","options":{"raw":{"language":"json"}}},"url":"https://api.monsterapi.ai/apis/add-task"},"_postman_previewlanguage":"json","header":null,"cookie":[],"responseTime":null,"body":"{\n \"message\": \"Request accepted successfully\",\n \"process_id\": \"f0ca09e9-aad1-11ed-aed8-5d93517c8890\"\n}"},{"id":"761e68cc-968a-49fd-b699-9a387f57be10","name":"Fetch request status","originalRequest":{"method":"POST","header":[{"key":"Authorization","value":"Bearer 456"}],"body":{"mode":"raw","raw":"{\n \"process_id\" : \"f0ca09e9-aad1-11ed-aed8-5d93517c8890\"\n}","options":{"raw":{"language":"json"}}},"url":"https://api.monsterapi.ai/apis/task-status"},"_postman_previewlanguage":"json","header":null,"cookie":[],"responseTime":null,"body":"{\n \"message\": \"Request processed successfully\",\n \"response_data\": {\n \"process_id\": \"f0ca09e9-aad1-11ed-aed8-5d93517c8890\",\n \"status\": \"COMPLETED\",\n \"result\": {\n \"output\": [\n \"https://processed-model-result.s3.us-east-2.amazonaws.com/f0ca09e9-aad1-11ed-aed8-5d93517c8890_0.png\"\n ]\n },\n \"credit_used\": 5,\n \"overage\": 0\n }\n}"}],"_postman_id":"3fcbe73c-52ea-4d42-8f6d-521519021d95"},{"name":"Speech to Text","id":"43984dee-ef44-40fe-b382-5fdbb0c3feab","protocolProfileBehavior":{"disableBodyPruning":true},"request":{"auth":{"type":"noauth","isInherited":false},"method":"POST","header":[{"key":"Authorization","value":"Bearer 456"}],"body":{"mode":"raw","raw":"","options":{"raw":{"language":"json"}}},"url":"","description":"\n\nAll the AI models are executed asynchronously on Monster API.
\n
Thus, every AI Model API has 2 endpoints:
Speech to Text API allows you to transcribe any audio file using OpenAI-Whisper Large-v2 model.
\nOpenAI Whisper is an open-source automatic speech recognition (ASR) system trained on 680,000 hours of multilingual and multitask supervised data collected from the web.
\nLarge-v2 is a biggest version of whisper model and offers superior transcription quality.
MonsterAPI speech to text API costs as low as $0.075* for 1 hour of audio file transcription.
\n\n\n* Pricing varies on factors like the processing time and the length of file to be transcribed.
\n
Speech to Text API also supports Speaker Diarization.
\nSpeech to text API requires only a file URL that you'd like to transcribe.
\nThe file URL must end in an extension of one of these supported file formats:
\nm4a, mp3, mp4, mpeg, mpga, wav, webm, ogg
Our API supports both videos and audio files.
\nWe assume that you have your x-api-key and Auth Token handy. If you do not have one already, then follow these steps first:
\nheaders = {\n 'x-api-key': '123',\n 'Authorization': 'Bearer 456'\n}\n\nThis REST API works asynchronously and accepts the requests received from send-request API, for which the request status can be viewed using fetch-status API.
\nThis collection shows 2 examples on how to send request and fetch the request status for a speech to text transcription use-case.
\n{\n \"model\": \"whisper\",\n \"data\": {\n \"file\": \"https://upload.wikimedia.org/wikipedia/commons/2/2d/A_J_Cook_Speech_from_Lansbury's_Labour_Weekly.ogg\",\n \"transcription_format\": \"srt\",\n \"prompt\": \"\",\n \"language\": \"en\"\n }\n}\n\nThe parameters passed in data list are described below:
2. Example body for Image to Image Fetch Request Status:
\n\"process_id\" : \"\"\n\nThe parameters passed in above API request are described below:
\nThat's it! You only need these 2 requests to process your audio and video files and thus get a high fidelity transcription at ultra low cost.
\nExample input for a speech to text API request for plain text format:
\nExpected output:
\n\n\nWell, they should find out. I would like to know why was it suspended? Why is Mark suspended? What are the violations? Okay, because if the Church of Scientology is just paying them off, that's kind of weird.
\n
As you may notice in the above output, we received text output in plain text format. It doesn't include any timestamps.
\nExample input for a speech to text API request for srt format:
\nExpected output:
\n\n\n\"00:00:00,000 00:00:08,000:: Well, they should find out. I would like to know why was it suspended? Why is Mark suspended? What are the violations?\",
\n
\"00:00:08,000 00:00:12,000:: Okay, because if the Church of Scientology is just paying them off, that's kind of weird.\"
We received json output in srt format with sequence timestamps.
\nSpeech to Text API also supports word level timestamps.
\nYou can send a request as follows:
\nExample input for a speech to text API request for word level timestamp format:
\nExpected output:
\n\n\n\"00:00:00,000 00:00:00,360:: Well,\",
\n
\"00:00:00,420 00:00:00,540:: they\",
\"00:00:00,540 00:00:00,880:: should\",
\"00:00:00,880 00:00:01,260:: find\",
..
..
..
\"00:00:10,919 00:00:11,160:: off,\",
\"00:00:11,220 00:00:11,480:: that's\",
\"00:00:11,480 00:00:11,619:: kind\",
\"00:00:11,619 00:00:11,720:: of\",
\"00:00:11,720 00:00:12,000:: weird.\"
We received json output with each word carrying its start and end timestamp.
\nTo get details such as language detected, duration of audio and much more information, you can send transcription_format as verbose
The expected JSON output will look something like this:
\n\n\n\"duration\": \"12.0424375\",
\n
\"language\": \"en\",
\"text\": \" Well, they should find out. I would like to know why was it suspended? Why is Mark suspended? What are the violations? Okay, because if the Church of Scientology is just paying them off, that's kind of weird.\",
\"language_probability\": \"0.995022177696228\",
\"vad_options\": \"\",
\"segments\": [
{
\"start\": \"0.0\",
\"temperature\": \"0.0\",
\"words\": \"\",
\"avg_logprob\": \"-0.30796018861374763\",
\"no_speech_prob\": \"0.8712119460105896\",
\"end\": \"8.0\",
\"id\": \"1\",
\"text\": \" Well, they should find out. I would like to know why was it suspended? Why is Mark suspended? What are the violations?\",
\"seek\": \"1204\",
\"compression_ratio\": \"1.368421052631579\"
},
{
\"start\": \"8.0\",
\"temperature\": \"0.0\",
\"words\": \"\",
\"avg_logprob\": \"-0.30796018861374763\",
\"no_speech_prob\": \"0.8712119460105896\",
\"end\": \"12.0\",
\"id\": \"2\",
\"text\": \" Okay, because if the Church of Scientology is just paying them off, that's kind of weird.\",
\"seek\": \"1204\",
\"compression_ratio\": \"1.368421052631579\"
}
]
Based on your use-case requirement, you may choose any formatting type for the transcription output.
\n","urlObject":{"query":[],"variable":[]}},"response":[{"id":"422f325b-d8f4-4b59-b5d2-5ead85dd8478","name":"Send request","originalRequest":{"method":"POST","header":[{"key":"Authorization","value":"Bearer 456"},{"key":"Content-Type","value":"application/json"}],"body":{"mode":"raw","raw":"{\n \"model\": \"whisper\",\n \"data\": {\n \"file\": \"https://upload.wikimedia.org/wikipedia/commons/2/2d/A_J_Cook_Speech_from_Lansbury%27s_Labour_Weekly.ogg\",\n \"transcription_format\": \"srt\",\n \"prompt\": \"\",\n \"language\": \"en\"\n }\n}","options":{"raw":{"language":"json"}}},"url":"https://api.monsterapi.ai/apis/add-task"},"_postman_previewlanguage":"json","header":null,"cookie":[],"responseTime":null,"body":"{\n \"message\": \"Request accepted successfully\",\n \"process_id\": \"916fd4c1-d2fa-11ed-b90e-49a0369313e3\"\n}"},{"id":"61fd50a5-a755-42f4-a327-5fccd28ebbc1","name":"Fetch request status","originalRequest":{"method":"POST","header":[{"key":"Authorization","value":"Bearer 456"}],"body":{"mode":"raw","raw":"{\n \"process_id\" : \"f0ca09e9-aad1-11ed-aed8-5d93517c8890\"\n}","options":{"raw":{"language":"json"}}},"url":"https://api.monsterapi.ai/apis/task-status"},"_postman_previewlanguage":"json","header":null,"cookie":[],"responseTime":null,"body":"{\n \"message\": \"Request processed successfully\",\n \"response_data\": {\n \"process_id\": \"916fd4c1-d2fa-11ed-b90e-49a0369313e3\",\n \"status\": \"COMPLETED\",\n \"result\": {\n \"text\": \" In the field of the workers of Britain, a million miners with their wives and children, something like one tenth of the whole population of this country, have long called aloud for justice. If you were to believe all the things the capitalist press say about us, you would think that we were the most terrible people on earth. They tell you that we are never satisfied, that we are always striking, that we are never content with our wages, with our hours, or with the houses we live in. And yet, I want not only to defend the miners, but to appeal to the national conscience, to recognize the justice of our claim for safety and economic security. Underneath all the grime and coal dust, miners are human and courageous beings. I have some right to speak for them, not only because I happen to be Secretary of the Miners' Federation, but because I myself have toiled for 21 years in the pits. I know what the miners' life is in those dark dungeons of despair. I know what the miners' wife's life is. I wonder if those who abused the miners were made to work even for one year in the pits, crawling nine hours a day down the hut's narrow gallery, lying half naked at the coal face, sweating at a narrow seam, working in water or in excessive heat, living in a miner's role, and taking home week by week a miner's average pay, with a risk of terrible mutilation and death ever present. I wonder if these people would be quite so sure that it was those paid agitators who made the miners struggle for better treatment. But this hard, grueling work, deep in the bowels of the earth, amidst the gas, heat, oil, and water, which every day takes toll of several lives and many injuries, has to be done. Britain's whole economic life depends upon it. How, then, is Britain going to treat our men, who work and die that she may live? Our case is simple. We ask for safety and economic security. Today, up and down our coal fields, miners and his family are faced with sheer starvation. He is desperate. He will not, he cannot, stand present conditions much longer. He would be a traitor to his wife and children if he did. Until he is given safety in the mines, adequate compensation, hours of labor that do not make him a mere coal-getting medium, decent living conditions, there can be no peace in the British coal fields. It is said the industry cannot fail. Then the industry must be reorganized and remodeled technically and scientifically. If present owners have failed to do this, then it must be taken out of their hands and run by the nation, not for private profit or for royalty owners, but for the benefit of the old people. The old idea will not work any longer. The miner has fought and lost and fought again. Once more he will fight, and together with all the workers of Britain, he will win the great battle of human freedom.\"\n },\n \"credit_used\": 4,\n \"overage\": 0\n }\n}"}],"_postman_id":"43984dee-ef44-40fe-b382-5fdbb0c3feab"},{"name":"Text to Speech - Bark","id":"b959e60f-3700-4a21-8f97-cf4ddc032bc4","protocolProfileBehavior":{"disableBodyPruning":true},"request":{"auth":{"type":"noauth","isInherited":false},"method":"POST","header":[{"key":"Authorization","value":"Bearer 456"}],"body":{"mode":"raw","raw":"","options":{"raw":{"language":"json"}}},"url":"","description":"\n\nAll the AI models are executed asynchronously on Monster API.
\n
Thus, every AI Model API has 2 endpoints:
Text to Speech API allows you to convert text to an audio file using Suno AI Bark model.
\nBark is a transformer-based text-to-audio model created by Suno. Bark can generate highly realistic, multilingual speech as well as other audio - including music, background noise and simple sound effects.
\nCurrently Bark audio outputs cannot be more than 14 seconds duration.
\nMonsterAPI Text to speech Bark API costs as low as $0.015* for 10 seconds of audio generation.
\n\n\n* Pricing varies on factors like the processing time and the text length to be converted.
\n
Text to Speech API requires only a text that you'd like to convert to audio.
\nThis REST API works asynchronously and accepts the requests received from send-request API, for which the request status can be viewed using fetch-status API.
\nWe assume that you have your x-api-key and Auth Token handy. If you do not have one already, then follow these steps first:
\nheaders = {\n 'x-api-key': '123',\n 'Authorization': 'Bearer 456'\n}\n\nThis REST API works asynchronously and accepts the requests received from send-request API, for which the request status can be viewed using fetch-status API.
\nThis collection shows 2 examples on how to send request and fetch the request status for a text to speech generation use-case.
\n{\n \"model\": \"sunoai-bark\",\n \"data\": {\n \"prompt\": \"What's the meaning of life?\",\n \"speaker\": \"en_speaker_2\",\n \"sample_rate\": 26000,\n \"text_temp\": 0.6,\n \"waveform_temp\": 1.0\n }\n}\n\nThe parameters passed in data list are described below:
2. Example body for Text to Speech Fetch Request Status:
\n\"process_id\" : \"\"\n\nThe parameters passed in above API request are described below:
\nThat's it! You only need these 2 requests to generate an audio file from your provided text prompt at ultra low cost.
\nExample input for a text to speech API request:
\nExpected output audio file:
\nAudio file link: https://processed-model-result.s3.us-east-2.amazonaws.com/2b8b6007-02aa-11ee-8044-f78708c74372_0.wav
\nAs you may notice in the above output, we received an audio file link.
\nDifferent sample rates, speaker, text and waveform temperature will result in different quality or texture of voice in the output audio file.
\n","urlObject":{"query":[],"variable":[]}},"response":[{"id":"c428930a-955e-4751-8fec-7f80f1bcd5e8","name":"Send request","originalRequest":{"method":"POST","header":[{"key":"Authorization","value":"Bearer 456"},{"key":"Content-Type","value":"application/json"}],"body":{"mode":"raw","raw":"{\n \"model\": \"sunoai-bark\",\n \"data\": {\n \"prompt\": \"What's the meaning of life?\",\n \"speaker\": \"en_speaker_2\",\n \"sample_rate\": 26000,\n \"text_temp\": 0.6,\n \"waveform_temp\": 1.0\n }\n}","options":{"raw":{"language":"json"}}},"url":"https://api.monsterapi.ai/apis/add-task"},"_postman_previewlanguage":"json","header":null,"cookie":[],"responseTime":null,"body":"{\n \"message\": \"Request accepted successfully\",\n \"process_id\": \"9c5b1b0c-04b4-11ee-b021-ed896a1be257\"\n}"},{"id":"c0a176c5-c0a0-486e-9b61-a671c0f70fff","name":"Fetch request status","originalRequest":{"method":"POST","header":[{"key":"Authorization","value":"Bearer 456"}],"body":{"mode":"raw","raw":"{\n \"process_id\" : \"9c5b1b0c-04b4-11ee-b021-ed896a1be257\"\n}","options":{"raw":{"language":"json"}}},"url":"https://api.monsterapi.ai/apis/task-status"},"_postman_previewlanguage":"json","header":null,"cookie":[],"responseTime":null,"body":"{\n \"message\": \"Request processed successfully\",\n \"response_data\": {\n \"process_id\": \"9c5b1b0c-04b4-11ee-b021-ed896a1be257\",\n \"status\": \"COMPLETED\",\n \"result\": {\n \"output\": [\n \"https://processed-model-result.s3.us-east-2.amazonaws.com/9c5b1b0c-04b4-11ee-b021-ed896a1be257_0.wav\"\n ]\n },\n \"credit_used\": 18,\n \"overage\": 0\n }\n}"}],"_postman_id":"b959e60f-3700-4a21-8f97-cf4ddc032bc4"}],"event":[{"listen":"prerequest","script":{"id":"e9191b48-1528-4bea-8846-6db377a20352","type":"text/javascript","exec":[""]}},{"listen":"test","script":{"id":"7260de31-0a8f-4487-82e0-15c9cb6656a2","type":"text/javascript","exec":[""]}}],"variable":[{"key":"AdminAuthToken","value":""},{"key":"AuthToken","value":""},{"key":"x-api-key","value":""}]}