Document and Speech API

API ID 14100

Document to Markdown (PDF, Office, HTML), OCR, schema-guided JSON extraction from documents and images, text-to-speech (Kokoro, 28 US and UK English voices) and multilingual embeddings (bge-m3)

API Documentation

Endpoints

Request
Convert PDF, DOCX, PPTX, XLSX/XLS and HTML into clean Markdown (or structured JSON) ready for LLMs and RAG. Tables are kept as Markdown tables and scanned PDFs are OCR'd automatically. Upload the document as the "file" form field (max 20 MB). Office/HTML files take about 0.4 s; PDFs about 3.5 s per page. Large files return a job_id to poll.
Endpoint ID: 34829
POST https://zylalabs.com/api/14100/document+and+speech+api/34829/document+to+markdown+or+json+for+llms
INPUT PARAMETERS

Document to Markdown or JSON for LLMs — Endpoint Features

Object Description
Request Body Required File Binary

Free test requests remaining: 3 of 3.


INPUT PARAMETERS

API EXAMPLE RESPONSE
JSON
{
    "job_id": "4d60eeb7437b4799bf00aa33f7efff24",
    "status": "finished",
    "format": "html",
    "pages": null,
    "markdown": "[Home](/) | [About](/about)\n\n# Bluefield Logistics update 1\n\n## Compliance backup\n\nEmployee shipment safety estimate budget office network backup maintenance summary customer employee compliance schedule supplier. Network regional project margin supplier warehouse project safety vendor pipeline renewal policy audit policy renewal. Storage inspection vendor project estimate report vendor contract backup balance.\n\n* Pipeline balance contract warehouse project payment.\n* Vendor balance backup review payment audit.\n* Office safety inventory review regional quarterly.\n\n## Target regional\n\nServer supplier balance forecast invoice deployment budget shipment training office budget estimate training quarterly payment storage. Milestone schedule forecast project summary maintenance compliance audit schedule estimate warehouse summary inventory training inspection project training. Audit balance backup warehouse analysis target audit delivery margin shipment warehouse summary warehouse server office customer. Review estimate margin compliance backup schedule review growth forecast growth report budget. Storage target project office target deployment compliance project analysis report revenue maintenance regional analysis delivery policy summary account. Supplier vendor milestone server server summary analysis report deployment vendor regional training target regional audit payment.\n\n* Review report pipeline renewal shipment backup.\n* Inventory training renewal audit inspection invoice.\n* Growth renewal office summary safety revenue.\n\n## Policy renewal\n\nMilestone project schedule training milestone balance maintenance server customer server report balance. Maintenance inspection pipeline inventory review delivery milestone quarterly inventory backup inventory employee storage customer. Network safety margin margin shipment budget maintenance delivery margin milestone pipeline audit network inventory network review. Project inspection server target estimate contract quarterly target budget. Deployment audit training milestone budget forecast inventory office payment target safety forecast account server project compliance. Backup supplier margin customer analysis budget balance server employee target.\n\n* Warehouse compliance supplier shipment maintenance renewal.\n* Target balance office employee storage office.\n* Invoice supplier schedule compliance estimate quarterly.\n* Customer server network compliance revenue inventory.\n* Office warehouse budget milestone network quarterly.\n\n## Maintenance audit\n\nEmployee quarterly supplier estimate forecast project shipment pipeline shipment network inventory quarterly project budget review customer safety. Project schedule review schedule forecast inspection account compliance project forecast. Regional inspection network maintenance project forecast revenue payment. Inventory renewal schedule regional network review deployment margin inventory. Warehouse payment milestone account summary audit network summary growth payment training renewal schedule forecast employee estimate balance.\n\n* Policy summary policy balance deployment server.\n* Revenue delivery office storage forecast margin.\n\n## Quarterly audit\n\nSummary policy summary employee payment schedule contract budget inspection report invoice employee payment. Delivery deployment customer balance analysis forecast maintenance quarterly customer. Milestone milestone schedule regional schedule inspection quarterly summary. Balance analysis estimate growth inspection vendor inventory quarterly balance forecast review balance growth. Server balance milestone schedule revenue summary shipment revenue target report backup budget contract project. Contract policy schedule office shipment inventory contract vendor renewal customer forecast invoice training summary renewal.\n\n* Server training maintenance compliance storage budget.\n* Audit safety budget account balance target.\n* Payment review forecast customer balance revenue.\n\n| Item | Qty | Unit price | Total |\n| --- | --- | --- | --- |\n| Cable ties | 1 | $57.25 | $57.25 |\n| Copper wire | 32 | $4.50 | $144.00 |\n| Pallet wrap | 4 | $337.50 | $1,350.00 |\n| Label printer | 23 | $396.99 | $9,130.77 |\n| LED panels | 12 | $387.00 | $4,644.00 |\n| Pallet wrap | 34 | $95.25 | $3,238.50 |\n| Shelving unit | 11 | $283.99 | $3,123.89 |\n| Cable ties | 36 | $234.50 | $8,442.00 |\n\n(c) 2026",
    "seconds": 0.04
}
Document to Markdown or JSON for LLMs — CODE SNIPPETS

    curl --location 'https://zylalabs.com/api/14100/document+and+speech+api/34829/document+to+markdown+or+json+for+llms' \
    --header 'Content-Type: application/json' \ 
    --form 'image=@"FILE_PATH"'

Request
Extract plain text from images and scanned PDFs with Tesseract 5 (English). Upload a PNG, JPG, TIFF, BMP, GIF, WebP or PDF up to 20 MB as the "file" form field; get back the full text plus the text of each page. Typically about 0.5 s per image.
Endpoint ID: 34830
POST https://zylalabs.com/api/14100/document+and+speech+api/34830/ocr+for+images+and+scanned+pdfs
INPUT PARAMETERS

OCR for images and scanned PDFs — Endpoint Features

Object Description
Request Body Required File Binary

Free test requests remaining: 3 of 3.


INPUT PARAMETERS

API EXAMPLE RESPONSE
JSON
{
    "job_id": "60c5551c8a804d099fab18d9e19078b6",
    "status": "finished",
    "pages": 1,
    "text": "HUBRIS HARDWARE STORE\nReceipt #10427 2026-10-06\n\nCable ties (100) $4.99\nLabel printer tape $12.50\n\nLED panel 30W $38.00\nSubtotal $55.49\nTax 8% $4.44\n\nTOTAL $59.93",
    "page_text": [
        "HUBRIS HARDWARE STORE\nReceipt #10427 2026-10-06\n\nCable ties (100) $4.99\nLabel printer tape $12.50\n\nLED panel 30W $38.00\nSubtotal $55.49\nTax 8% $4.44\n\nTOTAL $59.93"
    ],
    "seconds": 0.34
}
OCR for images and scanned PDFs — CODE SNIPPETS

    curl --location 'https://zylalabs.com/api/14100/document+and+speech+api/34830/ocr+for+images+and+scanned+pdfs' \
    --header 'Content-Type: application/json' \ 
    --form 'image=@"FILE_PATH"'

Request
Natural-sounding text-to-speech with Kokoro-82M: 28 US and UK English voices (GET the voices endpoint for the list), speed 0.5-2.0, output as WAV, MP3 or OGG. Send "response": "json" to get the audio base64-encoded in audio_base64 along with its duration. Texts up to 5,000 characters.
Endpoint ID: 34831
POST https://zylalabs.com/api/14100/document+and+speech+api/34831/text+to+speech+with+28+natural+english+voices
INPUT PARAMETERS

Text to speech with 28 natural English voices — Endpoint Features

Object Description
Request Body Required Json

Free test requests remaining: 3 of 3.


INPUT PARAMETERS

API EXAMPLE RESPONSE
JSON
{
    "job_id": "60661fac7e2040d097836d0e0156f799",
    "status": "finished",
    "content_type": "audio/mpeg",
    "duration": 2.7,
    "seconds": 1.52,
    "audio_base64": "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...",
    "_note": "Response truncated for documentation purposes"
}
Text to speech with 28 natural English voices — CODE SNIPPETS

curl --location --request POST 'https://zylalabs.com/api/14100/document+and+speech+api/34831/text+to+speech+with+28+natural+english+voices' --header 'Authorization: Bearer YOUR_API_KEY' 

--data-raw '{"text": "Hello", "voice": "af_heart", "format": "mp3", "response": "json"}'

    
Request
Upload an invoice, receipt, form, résumé or ID (image, or a PDF of up to 5 pages, max 20 MB) as the "file" field, and pass the fields you want as a JSON Schema in the "schema" parameter. A vision LLM reads the document and returns JSON that fills your schema in the "data" field: no templates or training needed, any layout works. Field names and descriptions guide the extraction, e.g. {"type":"object","properties":{"vendor":{"type":"string"},"date":{"type":"string","description":"YYYY-MM-DD"},"total":{"type":"number"}}}. Optional "instructions" add hints such as "amounts without currency symbols". Typically ~4 seconds per document.
Endpoint ID: 34832
POST https://zylalabs.com/api/14100/document+and+speech+api/34832/extract+json+from+invoices+receipts+and+forms
INPUT PARAMETERS

Extract JSON from Invoices Receipts and Forms — Endpoint Features

Object Description
schema Required JSON Schema of the fields to extract (type object with properties)
instructions Optional Optional extra hints for the extraction (max 2000 characters)
Request Body Required File Binary

Free test requests remaining: 3 of 3.


INPUT PARAMETERS

schema
instructions
API EXAMPLE RESPONSE
JSON
{
    "job_id": "6d31305ea8374de694af9ecc6ac250a5",
    "status": "finished",
    "data": {
        "vendor": "BLUEFIELD LOGISTICS",
        "date": "null",
        "total": 285.94
    },
    "pages": 1,
    "model": "Qwen3.5-9B",
    "seconds": 2.02,
    "usage": {
        "completion_tokens": 27,
        "prompt_tokens": 1063,
        "total_tokens": 1090,
        "prompt_tokens_details": {
            "cached_tokens": 84
        }
    }
}
Extract JSON from Invoices Receipts and Forms — CODE SNIPPETS

    curl --location 'https://zylalabs.com/api/14100/document+and+speech+api/34832/extract+json+from+invoices+receipts+and+forms?schema={"type":"object","properties":{"vendor":{"type":"string"},"date":{"type":"string","description":"YYYY-MM-DD"},"total":{"type":"number"}}}&instructions=Dates as YYYY-MM-DD' \
    --header 'Content-Type: application/json' \ 
    --form 'image=@"FILE_PATH"'

Request
Text embeddings for search and RAG (bge-m3, 1024 dimensions, 100+ languages)
Endpoint ID: 34833
POST https://zylalabs.com/api/14100/document+and+speech+api/34833/text+embeddings+bge-m3+for+search+and+rag
INPUT PARAMETERS

Text embeddings bge-m3 for search and RAG — Endpoint Features

Object Description
Request Body Required Json

Free test requests remaining: 3 of 3.


INPUT PARAMETERS

API EXAMPLE RESPONSE
JSON
{
    "job_id": "d275efda77d8467f99fc107cfe4f9530",
    "status": "finished",
    "model": "bge-m3",
    "dimensions": 1024,
    "embeddings": [
        [
            -0.026360729709267616,
            0.018764957785606384,
            -0.007465451490134001,
            0.024926811456680298,
            -0.011918624863028526,
            -0.022795354947447777,
            -0.029500657692551613,
            -0.05387190356850624,
            -0.005154398735612631,
            0.013199728913605213,
            -0.015859287232160568,
            0.007968025282025337,
            -0.01810515485703945,
            -0.0034902130719274282,
            0.04218396171927452,
            0.022848404943943024,
            -0.0027197510935366154,
            -0.022968312725424767,
            -0.020967822521924973,
            -0.048570841550827026,
            -0.03551868721842766,
            -0.03674390912055969,
            -0.021996796131134033,
            -0.0378466360270977,
            0.03440004214644432,
            0.030576083809137344,
            -0.012621345929801464,
            -0.010804662480950356,
            0.0028817104175686836,
            -0.0016225868603214622,
            0.028794676065444946,
            0.05280519276857376,
            0.01899181492626667,
            -0.05515936017036438,
            0.00237692310474813,
            -0.05521969124674797,
            0.025227895006537437,
            -0.040771711617708206,
            -0.054062508046627045,
            0.023251738399267197,
            0.010812771506607533,
            -0.009886990301311016,
            0.005214867182075977,
            -0.037689875811338425,
            0.014732777141034603,
            -0.0053230030462145805,
            -0.012678484432399273,
            -0.020910998806357384,
            -0.034494541585445404,
            -0.03623286262154579,
            0.023694222792983055,
            0.029530471190810204,
            0.060599349439144135,
            -0.021792814135551453,
            0.03344278782606125,
            -0.016523288562893867,
            0.0004548763681668788,
            -0.022630248218774796,
            -0.04753171652555466,
            -0.0008694236748851836,
            -0.025471733883023262,
            0.06470111012458801,
            -0.002681863959878683,
            0.016415635123848915,
            0.030858619138598442,
            0.10868271440267563,
            -0.015142744407057762,
            -0.018294256180524826,
            -0.008536950685083866,
            -0.0315316841006279,
            -0.0012140825856477022,
            -0.030446304008364677,
            -0.000739442533813417,
            -0.0031105850357562304,
            -0.05223897844552994,
            0.05568265542387962,
            -0.03413974121212959,
            -0.041451677680015564,
            -0.006167836487293243,
            0.04239819943904877,
            0.011961838230490685,
            -0.002703039674088359,
            0.016253197565674782,
            0.04705644026398659,
            -0.02178058587014675,
            0.004941869061440229,
            -0.004976153373718262,
            0.059388820081949234,
            -0.03378630056977272,
            -0.02306383103132248,
            -0.035514093935489655,
            -0.04526302218437195,
            0.009810909628868103,
            -0.03577648103237152,
            -0.014204704202711582,
            0.024884240701794624,
            -0.04254372790455818,
            -0.010117442347109318,
            0.010688691399991512,
            0.043652284890413284,
            0.021675702184438705,
            -0.0136497113853693,
            -0.009737011976540089,
            0.00648632412776351,
            0.00933374185115099,
            -0.013440796174108982,
            0.035029225051403046,
            0.07545912265777588,
            -0.0006574299768544734,
            -0.005496761295944452,
            0.03268790245056152,
            0.024570252746343613,
            0.016294902190566063,
            0.008444990031421185,
            0.020723726600408554,
            0.003495030337944627,
            -0.03971812501549721,
            0.003446533577516675,
            0.005315307527780533,
            -0.032830607146024704,
            0.007657879032194614,
            0.027274420484900475,
            -0.012719890102744102,
            0.02506241388618946,
            0.007452381309121847,
            -0.01969764567911625,
            -0.014745966531336308,
            -0.008699949830770493,
            0.02562093175947666,
            0.0023522297851741314,
            0.04362804442644119,
            0.01853683777153492,
            -0.013786775059998035,
            -0.003429254749789834,
            -0.014507939107716084,
            -0.03990774229168892,
            0.03778070956468582,
            0.005367587320506573,
            -0.02554490976035595,
            -0.049115438014268875,
            0.01562996208667755,
            0.06428598612546921,
            -0.028048783540725708,
            -0.0247585941106081,
            -0.03885119780898094,
            -0.04814241826534271,
            -0.016871575266122818,
            0.018553076311945915,
            0.014096802100539207,
            -0.012205495499074459,
            -0.027328744530677795,
            -0.020212912932038307,
            0.06968367844820023,
            0.024447796866297722,
            0.06652278453111649,
            -0.0038924841210246086,
            -0.005456226412206888,
            0.05486603453755379,
            -0.0009693393367342651,
            0.03548533841967583,
            -0.028079718351364136,
            -0.023844869807362556,
            -0.02958451583981514,
            0.015281638130545616,
            -0.027654215693473816,
            0.010093390941619873,
            0.005121355876326561,
            0.052305880934000015,
            0.002288642805069685,
            -0.04296610504388809,
            0.007336345501244068,
            -0.004735623486340046,
            0.018085116520524025,
            -0.01267689373344183,
            0.009503545239567757,
            0.04103822633624077,
            0.026547828689217567,
            0.012335679493844509,
            0.03424929454922676,
            -0.02306639775633812,
            -0.02233755588531494,
            0.007363742683082819,
            0.010557367466390133,
            -0.015589335933327675,
            -0.04994513466954231,
            -0.0017673952970653772,
            -0.04651610553264618,
            -0.015069488435983658,
            0.006461564917117357,
            0.013935538940131664,
            0.025145448744297028,
            -0.025112641975283623,
            0.07442934811115265,
            -0.03485783934593201,
            -0.03515983372926712,
            0.0054630436934530735,
            0.008485461585223675,
            -0.01399548351764679,
            0.011368869803845882,
            -0.02012605592608452,
            0.001742363441735506,
            0.0061524310149252415,
            0.0204410832375288,
            0.017167026177048683,
            -0.023108499124646187,
            -0.019477631896734238,
            -0.031186221167445183,
            -0.0004516954650171101,
            0.03420484811067581,
            -0.035895947366952896,
            0.03464173153042793,
            0.03564910590648651,
            -0.0041493624448776245,
            -0.04278682917356491,
            -0.032659098505973816,
            0.006934456992894411,
            -0.009885755367577076,
            -0.03598635271191597,
            -0.022954978048801422,
            -0.00023759105533827096,
            -0.0005521749262697995,
            0.020538590848445892,
            0.02561470866203308,
            0.01634577475488186,
            -0.04337653890252113,
            -0.005331628490239382,
            0.023266717791557312,
            0.03841116651892662,
            0.05753679946064949,
            0.01342632807791233,
            0.01992563158273697,
            0.003927210811525583,
            0.004954200703650713,
            0.0005482781562022865,
            -0.0021916499827057123,
            -0.008058175444602966,
            -0.029620831832289696,
            -0.00897140521556139,
            0.06203410401940346,
            0.02402571216225624,
            -0.013290688395500183,
            0.019747020676732063,
            0.016106197610497475,
            0.006350453943014145,
            -0.056829310953617096,
            0.01231817714869976,
            0.0160685908049345,
            -0.005774270743131638,
            -0.015509321354329586,
            0.0068002124316990376,
            0.013525455258786678,
            -0.030448010191321373,
            -0.02010527066886425,
            -0.002213766798377037,
            0.014676295220851898,
            0.0022204448468983173,
            -0.0009131305268965662,
            -0.0023590170312672853,
            -0.022702764719724655,
            -0.014960271306335926,
            0.041885364800691605,
            -0.01938743330538273,
            0.020955916494131088,
            0.048711635172367096,
            0.010495348833501339,
            -0.03489387035369873,
            -0.0054738461039960384,
            -0.010351249016821384,
            0.020315270870923996,
            -0.01622210070490837,
            -0.01045819092541933,
            0.0015500052832067013
        ]
    ],
    "_note": "Response truncated for documentation purposes"
}
Text embeddings bge-m3 for search and RAG — CODE SNIPPETS

curl --location --request POST 'https://zylalabs.com/api/14100/document+and+speech+api/34833/text+embeddings+bge-m3+for+search+and+rag' --header 'Authorization: Bearer YOUR_API_KEY' 

--data-raw '{"input": ["Zyla test: hello world", "Hola mundo"]}'

    
Request
Check a job and get its result. Calls that take longer than ~25 seconds (large PDFs, long audio) return 202 with a job_id; poll this endpoint every few seconds until status is finished. Results are kept for 1 hour.
Endpoint ID: 34834
GET https://zylalabs.com/api/14100/document+and+speech+api/34834/status+or+result+of+a+job
INPUT PARAMETERS

Free test requests remaining: 3 of 3.

API EXAMPLE RESPONSE
JSON
{
    "job_id": "420ebb435a894683baf45a85fc674cde",
    "status": "finished",
    "model": "bge-m3",
    "dimensions": 1024,
    "embeddings": [
        [
            -0.0464722141623497,
            -0.0018667300464585423,
            -0.0371648445725441,
            -0.009128189645707607,
            0.011508219875395298,
            0.04879334941506386,
            0.015451546758413315,
            0.011637936346232891,
            0.034409407526254654,
            -0.007657396141439676,
            -0.01718863658607006,
            -0.019426468759775162,
            0.006983604747802019,
            0.01361076720058918,
            0.0494811125099659,
            -0.030538933351635933,
            -0.015728916972875595,
            0.0007744300528429449,
            -0.04071548953652382,
            -0.0330025739967823,
            -0.039925795048475266,
            -0.025349698960781097,
            0.010481111705303192,
            0.057725097984075546,
            0.011553547345101833,
            0.006938023492693901,
            -0.01945289596915245,
            -0.047777432948350906,
            -0.017929373309016228,
            0.0027489946223795414,
            0.003945751115679741,
            -0.04622490331530571,
            -0.020068638026714325,
            -0.08855994790792465,
            -0.045495182275772095,
            -0.035786472260951996,
            0.02050005830824375,
            -0.031626515090465546,
            -0.049680195748806,
            0.00398241076618433,
            -0.0023152255453169346,
            0.012826946564018726,
            0.02726365067064762,
            -0.027217792347073555,
            0.008314336650073528,
            0.005185307469218969,
            0.008466667495667934,
            -0.021499808877706528,
            -0.04424712061882019,
            -0.018370209261775017,
            0.01171082817018032,
            0.008884216658771038,
            0.042054060846567154,
            0.0034155442845076323,
            0.04031505435705185,
            0.03222887963056564,
            0.024272514507174492,
            -0.037696607410907745,
            -0.06825398653745651,
            -0.03233516588807106,
            -0.020708123221993446,
            0.011472361162304878,
            0.00086175836622715,
            0.04094948619604111,
            0.013321088626980782,
            0.055446844547986984,
            0.017140628769993782,
            -0.019343767315149307,
            -0.004147707484662533,
            -0.03056744486093521,
            0.004836360923945904,
            0.0013437174493446946,
            -0.021837634965777397,
            0.019759703427553177,
            -0.01777702011168003,
            0.01743345707654953,
            0.008633836172521114,
            -0.02843315154314041,
            0.028702376410365105,
            -0.037460438907146454,
            -0.0084969038143754,
            0.01530237402766943,
            0.05886835232377052,
            0.00046952831326052547,
            -0.026879440993070602,
            0.0400034636259079,
            0.008436971344053745,
            -0.02091202139854431,
            -0.016855046153068542,
            0.015823140740394592,
            -0.018825754523277283,
            -0.040846049785614014,
            -0.004408090841025114,
            -0.02648300863802433,
            -0.040101807564496994,
            -0.016749117523431778,
            -0.04772195965051651,
            -0.010729881934821606,
            0.027728412300348282,
            0.0019339262507855892,
            -0.011177168227732182,
            -0.02008754573762417,
            0.016928447410464287,
            -0.023115191608667374,
            0.017816731706261635,
            0.010031859390437603,
            0.020718436688184738,
            0.013339154422283173,
            0.0018963207257911563,
            -0.010392547585070133,
            -0.00877289567142725,
            0.024962516501545906,
            0.045488886535167694,
            0.023440444841980934,
            0.008258449845016003,
            0.020473893731832504,
            -0.034598059952259064,
            -0.0033499712590128183,
            -0.010949326679110527,
            -0.017089439556002617,
            0.05098043754696846,
            0.002991704037413001,
            0.041186586022377014,
            -0.010161809623241425,
            -0.031187754124403,
            -0.05424121394753456,
            0.06293237209320068,
            0.017815077677369118,
            -0.04369242116808891,
            0.008646943606436253,
            -0.01110359001904726,
            0.07353390753269196,
            0.011732999235391617,
            -0.02814331464469433,
            -0.010894393548369408,
            -0.010577546432614326,
            0.0036510229110717773,
            -0.031166592612862587,
            -0.027768298983573914,
            -0.03477654978632927,
            0.01739451102912426,
            0.044342316687107086,
            -0.05605946108698845,
            -0.020559972152113914,
            -0.010283729992806911,
            -0.050063177943229675,
            0.040562279522418976,
            -0.0283510722219944,
            0.03121195361018181,
            -0.015744095668196678,
            -0.008543476462364197,
            0.0075677912682294846,
            0.0012113056145608425,
            -0.0011313175782561302,
            0.022773947566747665,
            0.0023159184493124485,
            -0.007789902854710817,
            -0.03465811908245087,
            0.004510392434895039,
            0.008851181715726852,
            0.0020095522049814463,
            0.05717214569449425,
            0.0032303754705935717,
            -0.005827932618558407,
            0.013640484772622585,
            0.0033684824593365192,
            0.022314071655273438,
            0.00918507482856512,
            0.011055565439164639,
            0.038446735590696335,
            0.023560727015137672,
            -0.06813052296638489,
            0.03183702379465103,
            -0.0460469014942646,
            0.017754483968019485,
            -0.0005308958934620023,
            0.08856499940156937,
            0.025330884382128716,
            0.00024640955962240696,
            -0.06118129938840866,
            -0.0065500992350280285,
            0.051926661282777786,
            0.03907697647809982,
            -0.02336634323000908,
            0.03454245999455452,
            -0.02669147215783596,
            0.023308400064706802,
            -0.007883391343057156,
            0.020292211323976517,
            -0.01773812063038349,
            -0.036671653389930725,
            -0.05205804482102394,
            0.030682742595672607,
            0.014629908837378025,
            0.023230653256177902,
            -0.04022481292486191,
            -0.016164127737283707,
            0.02155168168246746,
            0.02456062287092209,
            -0.010706563480198383,
            -0.030085759237408638,
            0.00530208507552743,
            -0.01380317471921444,
            -0.03822498023509979,
            -0.02491959184408188,
            0.014431408606469631,
            0.014309209771454334,
            -0.00018843795987777412,
            0.014814216643571854,
            -0.014504627324640751,
            -0.01074131578207016,
            0.002775700995698571,
            0.042363397777080536,
            0.016911180689930916,
            -0.013178769499063492,
            0.015393322333693504,
            0.057125795632600784,
            0.025147423148155212,
            -0.03010047785937786,
            -0.03155706450343132,
            0.02414689213037491,
            0.02935827523469925,
            0.045364975929260254,
            -0.032679080963134766,
            0.010364155285060406,
            0.013870828785002232,
            -0.008622677996754646,
            0.047169171273708344,
            0.046908292919397354,
            -0.0637698546051979,
            -0.007569996174424887,
            -0.015182774513959885,
            -0.03257399797439575,
            -0.018678272143006325,
            0.05370526388287544,
            -0.004776162561029196,
            -0.01430339552462101,
            0.02167040854692459,
            0.026628518477082253,
            0.010121233761310577,
            -0.062302619218826294,
            -0.024182153865695,
            0.04388730973005295,
            -0.0034580978099256754,
            -0.009360144846141338,
            -0.022418197244405746,
            0.029929164797067642,
            -0.00974380224943161,
            -0.0024123096372932196,
            -0.03111542947590351,
            0.015530704520642757,
            -0.005492634139955044,
            -0.04957010969519615,
            -0.05983327701687813,
            -0.025912189856171608,
            0.0059614940546453,
            -0.01065615750849247,
            -0.011005737818777561,
            0.013065936043858528,
            0.026562023907899857,
            -0.005515015684068203,
            -0.029546357691287994,
            -0.011400340124964714,
            0.01027169544249773,
            -0.017688127234578133,
            -0.0008369974093511701,
            -0.03785133361816406,
            0.0217633917927742,
            -0.027125390246510506,
            0.0003934203996323049,
            -0.027475636452436447,
            -0.0009278383222408593,
            0.02899765782058239
        ]
    ],
    "_note": "Response truncated for documentation purposes"
}
Status or result of a job — CODE SNIPPETS

curl --location --request GET 'https://zylalabs.com/api/14100/document+and+speech+api/34834/status+or+result+of+a+job&job_id=Required' --header 'Authorization: Bearer YOUR_API_KEY' 


    
Request
Lists the 28 voice IDs accepted by the text-to-speech endpoint (US and UK English, female and male voices). Use one as the "voice" field of POST /v1/tts.
Endpoint ID: 34836
GET https://zylalabs.com/api/14100/document+and+speech+api/34836/available+tts+voices
INPUT PARAMETERS

Free test requests remaining: 3 of 3.

This endpoint does not require any input parameters.

API EXAMPLE RESPONSE
JSON
{
    "voices": [
        "af_alloy",
        "af_aoede",
        "af_bella",
        "af_heart",
        "af_jessica",
        "af_kore",
        "af_nicole",
        "af_nova",
        "af_river",
        "af_sarah",
        "af_sky",
        "am_adam",
        "am_echo",
        "am_eric",
        "am_fenrir",
        "am_liam",
        "am_michael",
        "am_onyx",
        "am_puck",
        "am_santa",
        "bf_alice",
        "bf_emma",
        "bf_isabella",
        "bf_lily",
        "bm_daniel",
        "bm_fable",
        "bm_george",
        "bm_lewis"
    ]
}
Available TTS voices — CODE SNIPPETS

curl --location --request GET 'https://zylalabs.com/api/14100/document+and+speech+api/34836/available+tts+voices' --header 'Authorization: Bearer YOUR_API_KEY' 


    

API Access Key & Authentication

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 Document and Speech API simply include your bearer token in the Authorization header.

Headers
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.

Starts at
$10,000/Year


  • Custom Volume
  • Custom Rate Limit
  • Specialized Customer Support
  • Real-Time API Monitoring

Overview

Document to Markdown (PDF, Office, HTML), OCR, schema-guided JSON extraction from documents and images, text-to-speech (Kokoro, 28 US and UK English voices) and multilingual embeddings (bge-m3)

Document and Speech API FAQs

Files up to 20 MB. Document to Markdown accepts PDF (up to 50 pages), DOCX, PPTX, XLSX, XLS and HTML; scanned PDF pages are OCR'd automatically. OCR accepts PNG, JPG, TIFF, BMP, GIF, WebP and PDF. Data extraction accepts images and PDFs of up to 5 pages. Send the file in the "file" field; its name's extension tells the API the file type.

Call "Extract JSON from Invoices Receipts and Forms" with the document in the "file" field and a JSON Schema in the "schema" parameter, for example {"type":"object","properties":{"vendor":{"type":"string"},"date":{"type":"string","description":"YYYY-MM-DD"},"total":{"type":"number"}}}. The response's "data" field holds JSON that fills your schema. Descriptive field names and descriptions improve results, and the optional "instructions" parameter adds hints. No templates or training are needed, so any layout works.

No. Files are processed in memory on dedicated servers and deleted as soon as the job ends (always within 15 minutes). Results are kept for at most 1 hour so you can fetch them, then deleted. Nothing is shared, sold or used to train any model.

Most calls finish within 25 seconds and return the result directly. Longer jobs (for example big PDFs) return a job_id with status "queued" or "started". Poll the "Status or result of a job" endpoint with that job_id every few seconds until the status is "finished"; the response then contains the full result. Results are kept for 1 hour.

Text to speech is English with 28 natural voices: US female (af_), US male (am_), UK female (bf_) and UK male (bm_), for example af_heart, am_adam, bf_emma or bm_george. The "Available TTS voices" endpoint lists them all. Set "response" to "json" to receive the audio base64-encoded as audio_base64 (WAV, MP3 or OGG). OCR reads English. Document conversion and extraction work on documents in any Latin-script language, and embeddings (bge-m3) cover 100+ languages.

General FAQs

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.

Prices are listed in USD (United States Dollar), EUR (Euro), CAD (Canadian Dollar), AUD (Australian Dollar), and GBP (British Pound). We accept all major debit and credit cards. Our payment system uses the latest security technology and is powered by Stripe, one of the world's most reliable payment companies. If you have any trouble paying by card, just contact us at [email protected]

Additionally, if you already have an active subscription in any of these currencies (USD, EUR, CAD, AUD, GBP), that currency will remain for subsequent subscriptions. You can change the currency at any time as long as you don't have any active subscriptions.
The local currency shown on the pricing page is based on the country of your IP address and is provided for reference only. The actual prices are in USD (United States Dollar). When you make a payment, the charge will appear on your card statement in USD, even if you see the equivalent amount in your local currency on our website. This means you cannot pay directly with your local currency.
Occasionally, a bank may decline the charge due to its fraud protection settings. We suggest reaching out to your bank initially to check if they are blocking our charges. Also, you can access the Billing Portal and change the card associated to make the payment. If these does not work and you need further assistance, please contact our team at [email protected]
Prices are determined by a recurring monthly or yearly subscription, depending on the chosen plan.
API calls are deducted from your plan based on successful requests. Each plan comes with a specific number of calls that you can make per month. Only successful calls, indicated by a Status 200 response, will be counted against your total. This ensures that failed or incomplete requests do not impact your monthly quota.
Zyla API Hub works on a recurring monthly subscription system. Your billing cycle will start the day you purchase one of the paid plans, and it will renew the same day of the next month. So be aware to cancel your subscription beforehand if you want to avoid future charges.
To upgrade your current subscription plan, simply go to the pricing page of the API and select the plan you want to upgrade to. The upgrade will be instant, allowing you to immediately enjoy the features of the new plan. Please note that any remaining calls from your previous plan will not be carried over to the new plan, so be aware of this when upgrading. You will be charged the full amount of the new plan.
To check how many API calls you have left for the current month, refer to the 'X-Zyla-API-Calls-Monthly-Remaining' field in the response header. For example, if your plan allows 1,000 requests per month and you've used 100, this field in the response header will indicate 900 remaining calls.

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.

The 'X-Zyla-RateLimit-Reset' header shows the number of seconds until your rate limit resets. This tells you when your request count will start fresh. For example, if it displays 3,600, it means 3,600 seconds are left until the limit resets.

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.

After 7 days, you will be charged the full amount for the plan you were subscribed to during the trial. Therefore, it's important to cancel before the trial period ends. Refund requests for forgetting to cancel on time are not accepted.
When you subscribe to an API free trial, you can make up to 50 API calls. If you wish to make additional API calls beyond this limit, the API will prompt you to perform an "Start Your Paid Plan." You can find the "Start Your Paid Plan" button in your profile under Subscription -> Choose the API you are subscribed to -> Pricing tab.
You can contact us through our chat channel to receive immediate assistance. We are always online from 8 am to 5 pm (EST). If you reach us after that time, we will get back to you as soon as possible. Additionally, you can contact us via email at [email protected]

Please have a look at our Refund Policy: https://zylalabs.com/terms#refund


Related APIs