{"info":{"_postman_id":"369c7d65-3244-4331-b8b7-b1314983ad3e","name":"Speech Expert API — Speech-to-text and text-to-speech","description":"

Public API examples for Russian, Armenian, Uzbek, Kazakh, Kyrgyz and Tajik speech recognition, plus basic SpeechExpert-TTS synthesis.

Get an API key from Speech Expert.
Set api_key locally in Postman; keep its shared/exported value empty.
For STT, select an audio file in the request body and send one example. For TTS, first list voices and select a voice supported for the chosen language.

Requests use account credits according to the current service terms. See the linked documentation for model capabilities, pricing and data-processing terms.

Quick start · API documentation

\n","schema":"https://schema.getpostman.com/json/collection/v2.0.0/collection.json","toc":[],"owner":"60071113","collectionId":"369c7d65-3244-4331-b8b7-b1314983ad3e","publishedId":"2sBYHYuy3E","public":true,"customColor":{"top-bar":"FFFFFF","right-sidebar":"303030","highlight":"FF6C37"},"publishDate":"2026-11-09T18:52:16.000Z"},"item":[{"name":"Speech recognition — available models","item":[{"name":"Get STT capabilities","id":"0f0b6076-1af0-473c-8766-985d94c0116d","protocolProfileBehavior":{"disableBodyPruning":true},"request":{"auth":{"type":"noauth","isInherited":false},"method":"GET","header":[],"url":"https://speech-expert.ru/api/stt/capabilities","description":"

Retrieve the current published STT capabilities.

Public documentation.

\n","urlObject":{"path":["api","stt","capabilities"],"host":["https://speech-expert.ru"],"query":[],"variable":[]}},"response":[],"_postman_id":"0f0b6076-1af0-473c-8766-985d94c0116d"}],"id":"ecb9eba3-0419-4997-a905-55c0bdd69774","_postman_id":"ecb9eba3-0419-4997-a905-55c0bdd69774","description":"","auth":{"type":"apikey","apikey":{"basicConfig":[{"key":"key","value":"Authorization"},{"key":"value","value":""}]},"isInherited":true,"source":{"_postman_id":"369c7d65-3244-4331-b8b7-b1314983ad3e","id":"369c7d65-3244-4331-b8b7-b1314983ad3e","name":"Speech Expert API — Speech-to-text and text-to-speech","type":"collection"}}},{"name":"Speech recognition — file transcription","item":[{"name":"Russian — SpeechExpert-STT-RU","id":"dca3db07-7d67-4cae-85eb-447f711c58ae","protocolProfileBehavior":{"disableBodyPruning":true},"request":{"method":"POST","header":[],"body":{"mode":"formdata","formdata":[{"key":"file","type":"file","description":"

Choose an audio file before sending.

\n","value":null},{"key":"model","value":"SpeechExpert-STT-RU","type":"text"},{"key":"language","value":"ru","type":"text"},{"key":"response_format","value":"json","type":"text"},{"key":"stream","value":"false","type":"text"}]},"url":"https://speech-expert.ru/api/v1/audio/transcriptions","description":"

Select an audio file in Body > form-data.

Public documentation.

\n","auth":{"type":"bearer","bearer":{"basicConfig":[{"key":"token","value":""}]},"isInherited":true,"source":{"_postman_id":"b557e3fe-448c-41c1-872f-1fbc4a89b5b3","id":"b557e3fe-448c-41c1-872f-1fbc4a89b5b3","name":"Speech recognition — file transcription","type":"folder"}},"urlObject":{"path":["api","v1","audio","transcriptions"],"host":["https://speech-expert.ru"],"query":[],"variable":[]}},"response":[],"_postman_id":"dca3db07-7d67-4cae-85eb-447f711c58ae"},{"name":"Armenian — SpeechExpert-STT-HY-Large","id":"9c8b7146-9d23-4d79-a6bc-7b41a3a4992a","protocolProfileBehavior":{"disableBodyPruning":true},"request":{"method":"POST","header":[],"body":{"mode":"formdata","formdata":[{"key":"file","type":"file","description":"

Choose an audio file before sending.

\n","value":null},{"key":"model","value":"SpeechExpert-STT-HY-Large","type":"text"},{"key":"language","value":"hy","type":"text"},{"key":"response_format","value":"json","type":"text"},{"key":"stream","value":"false","type":"text"}]},"url":"https://speech-expert.ru/api/v1/audio/transcriptions","description":"

Select an audio file in Body > form-data. This model returns normalized Armenian text in lowercase without punctuation and uses external audio processing.

Public documentation.

\n","auth":{"type":"bearer","bearer":{"basicConfig":[{"key":"token","value":""}]},"isInherited":true,"source":{"_postman_id":"b557e3fe-448c-41c1-872f-1fbc4a89b5b3","id":"b557e3fe-448c-41c1-872f-1fbc4a89b5b3","name":"Speech recognition — file transcription","type":"folder"}},"urlObject":{"path":["api","v1","audio","transcriptions"],"host":["https://speech-expert.ru"],"query":[],"variable":[]}},"response":[],"_postman_id":"9c8b7146-9d23-4d79-a6bc-7b41a3a4992a"},{"name":"Uzbek — SpeechExpert-STT-UZ","id":"bce43546-02f6-495b-bef4-449948926506","protocolProfileBehavior":{"disableBodyPruning":true},"request":{"method":"POST","header":[],"body":{"mode":"formdata","formdata":[{"key":"file","type":"file","description":"

Choose an audio file before sending.

\n","value":null},{"key":"model","value":"SpeechExpert-STT-UZ","type":"text"},{"key":"language","value":"uz","type":"text"},{"key":"response_format","value":"json","type":"text"},{"key":"stream","value":"false","type":"text"}]},"url":"https://speech-expert.ru/api/v1/audio/transcriptions","description":"

Select an audio file in Body > form-data.

Public documentation.

\n","auth":{"type":"bearer","bearer":{"basicConfig":[{"key":"token","value":""}]},"isInherited":true,"source":{"_postman_id":"b557e3fe-448c-41c1-872f-1fbc4a89b5b3","id":"b557e3fe-448c-41c1-872f-1fbc4a89b5b3","name":"Speech recognition — file transcription","type":"folder"}},"urlObject":{"path":["api","v1","audio","transcriptions"],"host":["https://speech-expert.ru"],"query":[],"variable":[]}},"response":[],"_postman_id":"bce43546-02f6-495b-bef4-449948926506"},{"name":"Uzbek Large — SpeechExpert-STT-UZ-Large","id":"48d644e3-655d-4632-a8bb-5ce66e6d4975","protocolProfileBehavior":{"disableBodyPruning":true},"request":{"method":"POST","header":[],"body":{"mode":"formdata","formdata":[{"key":"file","type":"file","description":"

Choose an audio file before sending.

\n","value":null},{"key":"model","value":"SpeechExpert-STT-UZ-Large","type":"text"},{"key":"language","value":"uz","type":"text"},{"key":"response_format","value":"json","type":"text"},{"key":"stream","value":"false","type":"text"}]},"url":"https://speech-expert.ru/api/v1/audio/transcriptions","description":"

Select an audio file in Body > form-data.

Public documentation.

\n","auth":{"type":"bearer","bearer":{"basicConfig":[{"key":"token","value":""}]},"isInherited":true,"source":{"_postman_id":"b557e3fe-448c-41c1-872f-1fbc4a89b5b3","id":"b557e3fe-448c-41c1-872f-1fbc4a89b5b3","name":"Speech recognition — file transcription","type":"folder"}},"urlObject":{"path":["api","v1","audio","transcriptions"],"host":["https://speech-expert.ru"],"query":[],"variable":[]}},"response":[],"_postman_id":"48d644e3-655d-4632-a8bb-5ce66e6d4975"},{"name":"Kazakh — SpeechExpert-STT-KK-Large","id":"5ce12705-20fb-45b2-b987-464a7127e4b3","protocolProfileBehavior":{"disableBodyPruning":true},"request":{"method":"POST","header":[],"body":{"mode":"formdata","formdata":[{"key":"file","type":"file","description":"

Choose an audio file before sending.

\n","value":null},{"key":"model","value":"SpeechExpert-STT-KK-Large","type":"text"},{"key":"language","value":"kk","type":"text"},{"key":"response_format","value":"json","type":"text"},{"key":"stream","value":"false","type":"text"}]},"url":"https://speech-expert.ru/api/v1/audio/transcriptions","description":"

Select an audio file in Body > form-data. This profile uses external audio processing.

Public documentation.

\n","auth":{"type":"bearer","bearer":{"basicConfig":[{"key":"token","value":""}]},"isInherited":true,"source":{"_postman_id":"b557e3fe-448c-41c1-872f-1fbc4a89b5b3","id":"b557e3fe-448c-41c1-872f-1fbc4a89b5b3","name":"Speech recognition — file transcription","type":"folder"}},"urlObject":{"path":["api","v1","audio","transcriptions"],"host":["https://speech-expert.ru"],"query":[],"variable":[]}},"response":[],"_postman_id":"5ce12705-20fb-45b2-b987-464a7127e4b3"},{"name":"Kyrgyz — SpeechExpert-STT-KY-Large","id":"d5b623ee-f0ec-4337-be68-92791db34e91","protocolProfileBehavior":{"disableBodyPruning":true},"request":{"method":"POST","header":[],"body":{"mode":"formdata","formdata":[{"key":"file","type":"file","description":"

Choose an audio file before sending.

\n","value":null},{"key":"model","value":"SpeechExpert-STT-KY-Large","type":"text"},{"key":"language","value":"ky","type":"text"},{"key":"response_format","value":"json","type":"text"},{"key":"stream","value":"false","type":"text"}]},"url":"https://speech-expert.ru/api/v1/audio/transcriptions","description":"

Select an audio file in Body > form-data. This profile uses external audio processing.

Public documentation.

\n","auth":{"type":"bearer","bearer":{"basicConfig":[{"key":"token","value":""}]},"isInherited":true,"source":{"_postman_id":"b557e3fe-448c-41c1-872f-1fbc4a89b5b3","id":"b557e3fe-448c-41c1-872f-1fbc4a89b5b3","name":"Speech recognition — file transcription","type":"folder"}},"urlObject":{"path":["api","v1","audio","transcriptions"],"host":["https://speech-expert.ru"],"query":[],"variable":[]}},"response":[],"_postman_id":"d5b623ee-f0ec-4337-be68-92791db34e91"},{"name":"Tajik — SpeechExpert-STT-TG-Large","id":"7d492e6b-ca18-4168-8a61-3aac0550a3b6","protocolProfileBehavior":{"disableBodyPruning":true},"request":{"method":"POST","header":[],"body":{"mode":"formdata","formdata":[{"key":"file","type":"file","description":"

Choose an audio file before sending.

\n","value":null},{"key":"model","value":"SpeechExpert-STT-TG-Large","type":"text"},{"key":"language","value":"tg","type":"text"},{"key":"response_format","value":"json","type":"text"},{"key":"stream","value":"false","type":"text"}]},"url":"https://speech-expert.ru/api/v1/audio/transcriptions","description":"

Select an audio file in Body > form-data. This profile uses external audio processing.

Public documentation.

\n","auth":{"type":"bearer","bearer":{"basicConfig":[{"key":"token","value":""}]},"isInherited":true,"source":{"_postman_id":"b557e3fe-448c-41c1-872f-1fbc4a89b5b3","id":"b557e3fe-448c-41c1-872f-1fbc4a89b5b3","name":"Speech recognition — file transcription","type":"folder"}},"urlObject":{"path":["api","v1","audio","transcriptions"],"host":["https://speech-expert.ru"],"query":[],"variable":[]}},"response":[],"_postman_id":"7d492e6b-ca18-4168-8a61-3aac0550a3b6"}],"id":"b557e3fe-448c-41c1-872f-1fbc4a89b5b3","description":"

Seven model examples covering six languages. Choose one request and attach an audio file. JSON responses contain text. HY/KY/KK/TG Large profiles use external audio processing; see the model documentation for the applicable terms.

\n","auth":{"type":"bearer","bearer":{"basicConfig":[{"key":"token","value":""}]},"isInherited":false},"_postman_id":"b557e3fe-448c-41c1-872f-1fbc4a89b5b3"},{"name":"Speech recognition — background transcription","item":[{"name":"Start background transcription","id":"5083a859-6377-477d-a803-33e18f5b3338","protocolProfileBehavior":{"disableBodyPruning":true},"request":{"method":"POST","header":[],"body":{"mode":"formdata","formdata":[{"key":"audio","type":"file","description":"

Choose an audio file before sending.

\n","value":null},{"key":"lang","value":"ru-RU","type":"text"},{"key":"channelMode","value":"mono","type":"text"},{"key":"diarization","value":"false","type":"text"},{"key":"llmCorrection","value":"false","type":"text"}]},"url":"https://speech-expert.ru/api/stt/v1:recognizeAsync?model=SpeechExpert-STT-RU","description":"

Upload one file for background transcription. Set async_model and async_language to a compatible pair below. Copy the returned id into the local operation_id variable, then send Get operation status with the same API key.

\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n

Model	async_language
SpeechExpert-STT-RU	ru-RU
SpeechExpert-STT-HY-Large	hy-AM
SpeechExpert-STT-UZ	uz-UZ
SpeechExpert-STT-UZ-Large	uz-UZ
SpeechExpert-STT-KK-Large	kk-KZ
SpeechExpert-STT-KY-Large	ky-KG
SpeechExpert-STT-TG-Large	tg-TJ

HY/KY/KK/TG Large profiles use external audio processing; see the model documentation for terms.

Public documentation.

Set operation_id to the returned task id. If done is false, the task is still running. When done is true, check error; on success the STT v1 text is in response.result. Send this request again manually to refresh.

Public documentation.

Get voices available to your API key. Choose a returned name and set tts_voice for the synthesis example; match the voice and lang to your text.

Public documentation.

Synthesize a short Russian greeting with SpeechExpert-TTS. First confirm the example voice with List voices. The response is binary WAV audio.

Public documentation.

\n","auth":{"type":"apikey","apikey":{"basicConfig":[{"key":"key","value":"Authorization"},{"key":"value","value":""}]},"isInherited":true,"source":{"_postman_id":"369c7d65-3244-4331-b8b7-b1314983ad3e","id":"369c7d65-3244-4331-b8b7-b1314983ad3e","name":"Speech Expert API — Speech-to-text and text-to-speech","type":"collection"}},"urlObject":{"path":["api","tts","v1"],"host":["https://speech-expert.ru"],"query":[],"variable":[]}},"response":[],"_postman_id":"87f0b178-80d8-4ef5-8055-5c715803bd31"}],"id":"c33fd2eb-7add-421c-924c-8d060d8d9825","_postman_id":"c33fd2eb-7add-421c-924c-8d060d8d9825","description":"","auth":{"type":"apikey","apikey":{"basicConfig":[{"key":"key","value":"Authorization"},{"key":"value","value":""}]},"isInherited":true,"source":{"_postman_id":"369c7d65-3244-4331-b8b7-b1314983ad3e","id":"369c7d65-3244-4331-b8b7-b1314983ad3e","name":"Speech Expert API — Speech-to-text and text-to-speech","type":"collection"}}}],"auth":{"type":"apikey","apikey":{"basicConfig":[{"key":"key","value":"Authorization"},{"key":"value","value":""}]}},"variable":[{"key":"base_url","value":"https://speech-expert.ru","description":"Public API origin, without a trailing slash."},{"key":"api_key","value":"","description":"Set only in your local Postman environment. Keep shared/exported values empty."},{"key":"async_model","value":"SpeechExpert-STT-RU","description":"A documented model compatible with async_language."},{"key":"async_language","value":"ru-RU","description":"STT v1 BCP-47 language code matching async_model."},{"key":"operation_id","value":"","description":"Copy id from the successful Start background transcription response."},{"key":"tts_voice","value":"elena-speech-expert-tts","description":"Example Russian voice from the public documentation. Confirm the name with List voices before synthesis."}]}