> For the complete documentation index, see [llms.txt](https://docs.cloud.olakrutrim.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.cloud.olakrutrim.com/api-references/bhashik-speech-api.md).

# Bhashik Speech API

## Text to Speech

> Convert input text to an audio file in the specified language and speaker voice.

```json
{"openapi":"3.0.3","info":{"title":"Krutrim LanguageLabs APIs","version":"1.0.0"},"tags":[{"name":"Text-to-Speech"}],"servers":[{"url":"https://cloud.olakrutrim.com/api/v1"}],"security":[{"bearerAuth":[]}],"components":{"securitySchemes":{"bearerAuth":{"type":"http","scheme":"bearer","bearerFormat":"JWT"}},"schemas":{"TTSRequest":{"type":"object","required":["input_text","input_language","input_speaker"],"properties":{"input_text":{"type":"string","description":"Input text to synthesize."},"input_language":{"$ref":"#/components/schemas/LanguageShort"},"input_speaker":{"$ref":"#/components/schemas/Speaker"}}},"LanguageShort":{"type":"string","description":"Language code","enum":["eng","guj","ben","hin","kan","mal","mar","tam","tel"]},"Speaker":{"type":"string","enum":["female","male"]},"TTSResponse":{"type":"object","properties":{"status":{"type":"string"},"data":{"type":"object","properties":{"audio_file":{"type":"string","description":"Download URL for the generated audio file."}}}}},"Error":{"type":"object","properties":{"status":{"type":"string"},"message":{"type":"string"}}}}},"paths":{"/languagelabs/tts":{"post":{"tags":["Text-to-Speech"],"summary":"Text to Speech","description":"Convert input text to an audio file in the specified language and speaker voice.","requestBody":{"required":true,"content":{"application/json":{"schema":{"$ref":"#/components/schemas/TTSRequest"}}}},"responses":{"200":{"description":"Audio file link","content":{"application/json":{"schema":{"$ref":"#/components/schemas/TTSResponse"}}}},"400":{"description":"Bad request","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}},"401":{"description":"Unauthorized","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}}}}}}}
```

## Text to Speech Translation

> Translate input text from source language to target language and return synthesized speech.

```json
{"openapi":"3.0.3","info":{"title":"Krutrim LanguageLabs APIs","version":"1.0.0"},"tags":[{"name":"Text-to-Speech"},{"name":"Translation"}],"servers":[{"url":"https://cloud.olakrutrim.com/api/v1"}],"security":[{"bearerAuth":[]}],"components":{"securitySchemes":{"bearerAuth":{"type":"http","scheme":"bearer","bearerFormat":"JWT"}},"schemas":{"TTSTransRequest":{"type":"object","required":["input_text","src_lang_code","tgt_lang_code","input_speaker"],"properties":{"input_text":{"type":"string","description":"Input text to translate and synthesize."},"src_lang_code":{"$ref":"#/components/schemas/LanguageSrcOnlyEng"},"tgt_lang_code":{"$ref":"#/components/schemas/LanguageTarget"},"input_speaker":{"$ref":"#/components/schemas/Speaker"}}},"LanguageSrcOnlyEng":{"type":"string","enum":["eng"],"description":"Only 'eng' is supported as the source for certain translation endpoints."},"LanguageTarget":{"type":"string","description":"Target language code","enum":["eng","guj","ben","hin","kan","mal","mar","tam","tel"]},"Speaker":{"type":"string","enum":["female","male"]},"TTSTransResponse":{"allOf":[{"$ref":"#/components/schemas/TTSResponse"}]},"TTSResponse":{"type":"object","properties":{"status":{"type":"string"},"data":{"type":"object","properties":{"audio_file":{"type":"string","description":"Download URL for the generated audio file."}}}}},"Error":{"type":"object","properties":{"status":{"type":"string"},"message":{"type":"string"}}}}},"paths":{"/languagelabs/tts_trans":{"post":{"tags":["Text-to-Speech","Translation"],"summary":"Text to Speech Translation","description":"Translate input text from source language to target language and return synthesized speech.","requestBody":{"required":true,"content":{"application/json":{"schema":{"$ref":"#/components/schemas/TTSTransRequest"}}}},"responses":{"200":{"description":"Audio file link","content":{"application/json":{"schema":{"$ref":"#/components/schemas/TTSTransResponse"}}}},"400":{"description":"Bad request","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}},"401":{"description":"Unauthorized","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}}}}}}}
```

## Speech to Text (upload)

> Upload a short audio file (mp3, wav) and get transcribed text.

```json
{"openapi":"3.0.3","info":{"title":"Krutrim LanguageLabs APIs","version":"1.0.0"},"tags":[{"name":"Speech-to-Text"}],"servers":[{"url":"https://cloud.olakrutrim.com/api/v1"}],"security":[{"bearerAuth":[]}],"components":{"securitySchemes":{"bearerAuth":{"type":"http","scheme":"bearer","bearerFormat":"JWT"}},"schemas":{"STTUploadRequest":{"type":"object","required":["file","lang_code"],"properties":{"file":{"type":"string","format":"binary","description":"Audio file (mp3 or wav)."},"lang_code":{"$ref":"#/components/schemas/LanguageShort"}}},"LanguageShort":{"type":"string","description":"Language code","enum":["eng","guj","ben","hin","kan","mal","mar","tam","tel"]},"STTResponse":{"type":"object","properties":{"status":{"type":"string"},"data":{"type":"object","properties":{"text":{"type":"array","items":{"type":"string"},"description":"Transcribed text segments."}}}}},"Error":{"type":"object","properties":{"status":{"type":"string"},"message":{"type":"string"}}}}},"paths":{"/languagelabs/transcribe/upload":{"post":{"tags":["Speech-to-Text"],"summary":"Speech to Text (upload)","description":"Upload a short audio file (mp3, wav) and get transcribed text.","requestBody":{"required":true,"content":{"multipart/form-data":{"schema":{"$ref":"#/components/schemas/STTUploadRequest"}}}},"responses":{"200":{"description":"Transcribed text","content":{"application/json":{"schema":{"$ref":"#/components/schemas/STTResponse"}}}},"400":{"description":"Bad request","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}},"401":{"description":"Unauthorized","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}}}}}}}
```

## Speech to Text Translation (upload)

> Upload a short audio file (mp3, wav) and get translated text.

```json
{"openapi":"3.0.3","info":{"title":"Krutrim LanguageLabs APIs","version":"1.0.0"},"tags":[{"name":"Speech-to-Text"},{"name":"Translation"}],"servers":[{"url":"https://cloud.olakrutrim.com/api/v1"}],"security":[{"bearerAuth":[]}],"components":{"securitySchemes":{"bearerAuth":{"type":"http","scheme":"bearer","bearerFormat":"JWT"}},"schemas":{"STTTransUploadRequest":{"type":"object","required":["file","src_lang_code","tgt_lang_code"],"properties":{"file":{"type":"string","format":"binary","description":"Audio file (mp3 or wav)."},"src_lang_code":{"$ref":"#/components/schemas/LanguageSrcOnlyEng"},"tgt_lang_code":{"$ref":"#/components/schemas/LanguageTarget"}}},"LanguageSrcOnlyEng":{"type":"string","enum":["eng"],"description":"Only 'eng' is supported as the source for certain translation endpoints."},"LanguageTarget":{"type":"string","description":"Target language code","enum":["eng","guj","ben","hin","kan","mal","mar","tam","tel"]},"STTTransResponse":{"type":"object","properties":{"status":{"type":"string"},"data":{"type":"object","properties":{"translated_text":{"type":"string","description":"Translated text."}}}}},"Error":{"type":"object","properties":{"status":{"type":"string"},"message":{"type":"string"}}}}},"paths":{"/languagelabs/stt_trans/upload":{"post":{"tags":["Speech-to-Text","Translation"],"summary":"Speech to Text Translation (upload)","description":"Upload a short audio file (mp3, wav) and get translated text.","requestBody":{"required":true,"content":{"multipart/form-data":{"schema":{"$ref":"#/components/schemas/STTTransUploadRequest"}}}},"responses":{"200":{"description":"Translated text","content":{"application/json":{"schema":{"$ref":"#/components/schemas/STTTransResponse"}}}},"400":{"description":"Bad request","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}},"401":{"description":"Unauthorized","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}}}}}}}
```

## Speech to Speech Translation (upload)

> Upload a short audio file and receive translated synthesized speech.

```json
{"openapi":"3.0.3","info":{"title":"Krutrim LanguageLabs APIs","version":"1.0.0"},"tags":[{"name":"Translation"}],"servers":[{"url":"https://cloud.olakrutrim.com/api/v1"}],"security":[{"bearerAuth":[]}],"components":{"securitySchemes":{"bearerAuth":{"type":"http","scheme":"bearer","bearerFormat":"JWT"}},"schemas":{"STSUploadRequest":{"type":"object","required":["file","src_lang_code","tgt_lang_code","input_speaker"],"properties":{"file":{"type":"string","format":"binary","description":"Audio file (mp3 or wav)."},"src_lang_code":{"$ref":"#/components/schemas/LanguageSrcOnlyEng"},"tgt_lang_code":{"$ref":"#/components/schemas/LanguageTarget"},"input_speaker":{"$ref":"#/components/schemas/Speaker"}}},"LanguageSrcOnlyEng":{"type":"string","enum":["eng"],"description":"Only 'eng' is supported as the source for certain translation endpoints."},"LanguageTarget":{"type":"string","description":"Target language code","enum":["eng","guj","ben","hin","kan","mal","mar","tam","tel"]},"Speaker":{"type":"string","enum":["female","male"]},"STSResponse":{"type":"object","properties":{"status":{"type":"string"},"data":{"type":"object","properties":{"audio_file":{"type":"string","description":"Download URL for the translated synthesized audio."}}}}},"Error":{"type":"object","properties":{"status":{"type":"string"},"message":{"type":"string"}}}}},"paths":{"/languagelabs/sts_trans/upload":{"post":{"tags":["Translation"],"summary":"Speech to Speech Translation (upload)","description":"Upload a short audio file and receive translated synthesized speech.","requestBody":{"required":true,"content":{"multipart/form-data":{"schema":{"$ref":"#/components/schemas/STSUploadRequest"}}}},"responses":{"200":{"description":"Audio file link","content":{"application/json":{"schema":{"$ref":"#/components/schemas/STSResponse"}}}},"400":{"description":"Bad request","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}},"401":{"description":"Unauthorized","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}}}}}}}
```

## Long-duration Speech to Text (upload)

> Upload a longer audio file for asynchronous transcription; returns a request\_id that can be polled.

```json
{"openapi":"3.0.3","info":{"title":"Krutrim LanguageLabs APIs","version":"1.0.0"},"tags":[{"name":"Speech-to-Text"},{"name":"Long-Form"}],"servers":[{"url":"https://cloud.olakrutrim.com/api/v1"}],"security":[{"bearerAuth":[]}],"components":{"securitySchemes":{"bearerAuth":{"type":"http","scheme":"bearer","bearerFormat":"JWT"}},"schemas":{"STTUploadRequest":{"type":"object","required":["file","lang_code"],"properties":{"file":{"type":"string","format":"binary","description":"Audio file (mp3 or wav)."},"lang_code":{"$ref":"#/components/schemas/LanguageShort"}}},"LanguageShort":{"type":"string","description":"Language code","enum":["eng","guj","ben","hin","kan","mal","mar","tam","tel"]},"LongFormQueuedResponse":{"type":"object","properties":{"status":{"type":"string"},"data":{"type":"object","properties":{"request_id":{"type":"string","format":"uuid"},"status":{"type":"string","enum":["QUEUED"]}}}}},"Error":{"type":"object","properties":{"status":{"type":"string"},"message":{"type":"string"}}}}},"paths":{"/languagelabs/transcribe/lf/upload":{"post":{"tags":["Long-Form","Speech-to-Text"],"summary":"Long-duration Speech to Text (upload)","description":"Upload a longer audio file for asynchronous transcription; returns a request_id that can be polled.","requestBody":{"required":true,"content":{"multipart/form-data":{"schema":{"$ref":"#/components/schemas/STTUploadRequest"}}}},"responses":{"200":{"description":"Job queued","content":{"application/json":{"schema":{"$ref":"#/components/schemas/LongFormQueuedResponse"}}}},"400":{"description":"Bad request","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}},"401":{"description":"Unauthorized","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}}}}}}}
```

## Long-duration Speech to Text Translation (upload)

> Upload a longer audio file for asynchronous speech-to-text translation; returns a request\_id that can be polled.

```json
{"openapi":"3.0.3","info":{"title":"Krutrim LanguageLabs APIs","version":"1.0.0"},"tags":[{"name":"Translation"},{"name":"Long-Form"}],"servers":[{"url":"https://cloud.olakrutrim.com/api/v1"}],"security":[{"bearerAuth":[]}],"components":{"securitySchemes":{"bearerAuth":{"type":"http","scheme":"bearer","bearerFormat":"JWT"}},"schemas":{"STTTransLFUploadRequest":{"type":"object","required":["file","src_lang_code","tgt_lang_code"],"properties":{"file":{"type":"string","format":"binary","description":"Long audio file (mp3 or wav)."},"src_lang_code":{"$ref":"#/components/schemas/LanguageSrcOnlyEng"},"tgt_lang_code":{"$ref":"#/components/schemas/LanguageTarget"}}},"LanguageSrcOnlyEng":{"type":"string","enum":["eng"],"description":"Only 'eng' is supported as the source for certain translation endpoints."},"LanguageTarget":{"type":"string","description":"Target language code","enum":["eng","guj","ben","hin","kan","mal","mar","tam","tel"]},"LongFormQueuedResponse":{"type":"object","properties":{"status":{"type":"string"},"data":{"type":"object","properties":{"request_id":{"type":"string","format":"uuid"},"status":{"type":"string","enum":["QUEUED"]}}}}},"Error":{"type":"object","properties":{"status":{"type":"string"},"message":{"type":"string"}}}}},"paths":{"/languagelabs/stt_trans/lf/upload":{"post":{"tags":["Long-Form","Translation"],"summary":"Long-duration Speech to Text Translation (upload)","description":"Upload a longer audio file for asynchronous speech-to-text translation; returns a request_id that can be polled.","requestBody":{"required":true,"content":{"multipart/form-data":{"schema":{"$ref":"#/components/schemas/STTTransLFUploadRequest"}}}},"responses":{"200":{"description":"Job queued","content":{"application/json":{"schema":{"$ref":"#/components/schemas/LongFormQueuedResponse"}}}},"400":{"description":"Bad request","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}},"401":{"description":"Unauthorized","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}}}}}}}
```

## Get long-duration job status

> Poll the status of a long-duration transcription/translation job and obtain the output link/text when available.

```json
{"openapi":"3.0.3","info":{"title":"Krutrim LanguageLabs APIs","version":"1.0.0"},"tags":[{"name":"Long-Form"}],"servers":[{"url":"https://cloud.olakrutrim.com/api/v1"}],"security":[{"bearerAuth":[]}],"components":{"securitySchemes":{"bearerAuth":{"type":"http","scheme":"bearer","bearerFormat":"JWT"}},"schemas":{"JobStatusResponse":{"type":"object","properties":{"status":{"type":"string"},"data":{"type":"object","properties":{"request_id":{"type":"string"},"file_name":{"type":"string"},"file_size_mb":{"type":"number","format":"float"},"service_type":{"type":"string","description":"Service handling the job (e.g., stttransservice)."},"status":{"type":"string","description":"Current job status (e.g., QUEUED, RUNNING, FAILED, SUCCESS)."},"output_file":{"type":"string","nullable":true,"description":"Download URL for output (e.g., .txt) if SUCCESS."},"created_at":{"type":"string","format":"date-time"},"updated_at":{"type":"string","format":"date-time"}}}}},"Error":{"type":"object","properties":{"status":{"type":"string"},"message":{"type":"string"}}}}},"paths":{"/languagelabs/job_status/{request_id}":{"get":{"tags":["Long-Form"],"summary":"Get long-duration job status","description":"Poll the status of a long-duration transcription/translation job and obtain the output link/text when available.","parameters":[{"in":"path","name":"request_id","required":true,"schema":{"type":"string"},"description":"Request ID returned by the long-duration upload endpoint."}],"responses":{"200":{"description":"Job status payload","content":{"application/json":{"schema":{"$ref":"#/components/schemas/JobStatusResponse"}}}},"400":{"description":"Bad request","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}},"401":{"description":"Unauthorized","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}},"404":{"description":"Request ID not found","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}}}}}}}
```


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.cloud.olakrutrim.com/api-references/bhashik-speech-api.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.