> ## Documentation Index > Fetch the complete documentation index at: https://docs.reverieinc.com/llms.txt > Use this file to discover all available pages before exploring further. # Text to Speech API > Reverie’s TTS (Text-to-Speech) is a solution that turns text into lifelike speech, allowing you to create applications that talk in multiple Indic languages and build comprehensive speech-enabled products. ## OpenAPI ````yaml POST / openapi: 3.0.1 info: title: Localization API description: An API for translating text content into multiple languages version: 1.0.0 servers: - url: https://revapi.reverieinc.com security: [] paths: /: post: parameters: - name: Content-Type in: header required: true schema: type: string enum: - application/json example: application/json description: The format of the data to be posted. - name: REV-API-KEY in: header required: true schema: type: string example: description: >- A unique key/token provided by Reverie to identify the user using the Localization API. - name: REV-APP-ID in: header required: true schema: type: string example: description: >- The unique account ID to identify the user and the default account settings. - name: REV-APPNAME in: header required: true schema: type: string enum: - tts example: tts description: The parameter to identify the API. - name: speaker in: header required: true schema: type: string example: hi_male enum: - hi_male - hi_male_2 - hi_male_3 - hi_male_4 - hi_female - hi_female_2 - hi_female_3 - bn_male - bn_male_2 - bn_female - bn_female_2 - kn_male - kn_male_2 - kn_female - kn_female_2 - ml_male - ml_female - ta_male - ta_female - te_male - te_male_2 - te_female - te_female_2 - gu_male - gu_female - or_male - or_female - as_male - as_female - mr_male - mr_male_2 - mr_male_3 - mr_female - mr_female_2 - mr_female_3 - pa_male - pa_female - en_male - en_male_2 - en_female - en_female_2 description: >- The desired language and voice code for synthesizing the audio file requestBody: description: Text content to be generated to speech content: application/json: schema: $ref: '#/components/schemas/TTSRequest' required: true responses: '200': description: TTS response content: application/json: schema: $ref: '#/components/schemas/TTSResponse' '400': description: no spkr given content: application/json: schema: type: object properties: error: type: string description: The error message describing the issue. example: no spkr given description: type: string description: A detailed description of the error. example: Speaker code not entered required: - error - description '403': description: Invalid REV-API-KEY or REV-APP-ID content: application/json: schema: type: object properties: error: type: string description: The error message describing the issue. example: Invalid REV-API-KEY or REV-APP-ID description: type: string description: A detailed description of the error. example: Entered Invalid credentials required: - error - description x-codeSamples: - lang: curl source: |- curl --location --request POST 'https://revapi.reverieinc.com/' \ --header 'REV-API-KEY: ' \ --header 'REV-APP-ID: ' \ --header 'REV-APPNAME: tts' \ --header 'speaker: hi_female' \ --header 'Content-Type: application/json' \ --data-raw '{ "text": ["भारत मेरा देश है।", "मेरी कंपनी का नाम रेवेरी लैंग्वेज टेक्नोलॉजीज है।"], "speed": 1, "pitch": 0, "format": "WAV" }' - lang: javascript source: |- const ReverieClient = require("reverie-client"); const reverieClient = new ReverieClient({ apiKey: "YOUR-API-KEY", appId: "YOUR-APP-ID", }); try { const audioBlob = await reverieClient.text_to_speech({ text: text, speaker: speaker, speed: speed, pitch: pitch, }); const audioUrl = URL.createObjectURL(audioBlob); console.log("Audio URL is:", audioUrl); } catch (error) { console.error("Error:", error); } - lang: python source: |- from reverie_sdk import ReverieClient client = ReverieClient( api_key="MY_API_KEY", app_id="MY_APP_ID", ) with open("./big_text.txt", encoding="utf-8") as f: text = f.read() for resp_idx, resp in enumerate( client.tts.tts_streaming( text=text, speaker="en_male", max_words_per_chunk=5, fast_sentence_fragment=False, ) ): print(f"{resp_idx:08d} {resp.duration:10.3f}") resp.save_audio( f".path/to/output/{resp_idx:08d}.wav", create_parents=True, overwrite_existing=True, ) - lang: go source: "package main\n\nimport (\n\t\"bytes\"\n\t\"fmt\"\n\t\"io\"\n\t\"net/http\"\n\t\"os\"\n)\n\nfunc sendRequest(payload string, filename string) {\n\turl := \"https://revapi.reverieinc.com/\"\n\n\treq, err := http.NewRequest(\"POST\", url, bytes.NewBuffer([]byte(payload)))\n\tif err != nil {\n\t\tfmt.Println(\"Request creation error:\", err)\n\t\treturn\n\t}\n\n\t// Set Headers\n\treq.Header.Set(\"REV-API-KEY\", \"\")\n\treq.Header.Set(\"REV-APP-ID\", \"\")\n\treq.Header.Set(\"REV-APPNAME\", \"tts\")\n\treq.Header.Set(\"speaker\", \"hi_female\") //Set Speaker\n\treq.Header.Set(\"Content-Type\", \"application/json\")\n\n\tclient := &http.Client{}\n\tresp, err := client.Do(req)\n\tif err != nil {\n\t\tfmt.Println(\"Request error:\", err)\n\t\treturn\n\t}\n\tdefer resp.Body.Close()\n\n\t// Create a file to save the response\n\tfile, err := os.Create(filename)\n\tif err != nil {\n\t\tfmt.Println(\"File creation error:\", err)\n\t\treturn\n\t}\n\tdefer file.Close()\n\n\t// Copy response body to file\n\t_, err = io.Copy(file, resp.Body)\n\tif err != nil {\n\t\tfmt.Println(\"File write error:\", err)\n\t\treturn\n\t}\n\tfmt.Println(\"Audio saved as\", filename)\n}\n\nfunc main() {\n\t// Request 1: Plain text TTS\n\tpayload1 := `{\\n\\t\"text\": [\"भारत मेरा देश है।\", \"मेरी कंपनी का नाम रेवेरी लैंग्वेज टेक्नोलॉजीज है।\"],\\n\\t\"speed\": 1,\\n\\t\"pitch\": 0,\\n\\t\"format\": \"WAV\"\\n}`\nsendRequest(payload1, \"output1.wav\")\n\n\t// Request 2: SSML-based TTS\n\tpayload2 := `{\\n\\t\"ssml\": \" Hello. \",\\n\\t\"speed\": 1,\\n\\t\"pitch\": 0,\\n\\t\"format\": \"mp3\"\\n}`\nsendRequest(payload2, \"output2.mp3\")\n}" components: schemas: TTSRequest: type: object properties: text: type: array description: The text you want to process to generate the speech. items: type: string speed: type: number description: >- The speech rate of the audio file. Allows values from 0.5 (slowest speed) up to 1.5 (fastest speed). pitch: type: number description: >- Speaking pitch, in the range from -3 to 3. 3 indicates an increase of 3 semitones; -3 indicates a decrease of 3 semitones. sample_rate: type: integer description: The sampling rate (in hertz) to synthesize the audio output. format: type: string description: The speech audio format to generate the audio file (e.g., WAV, MP3). required: - text TTSResponse: type: string format: binary description: Audio data in MP3 format example: Audio Response ````