ashot72 / speech-to-text-to-image

Generating texts from your voice then images form the texts

Speech to Text to Image Generation

I just built an app where you can record your voice and see the text extracted from your voice and the image generated.

I turn my audio into text using Whisper which is an OpenAI Speech Recognition Model that turns audio into text with up to 99% accuracy. Whisper is a speech transcription system form the creators of ChatGPT. Anyone can use it, and it is completely free. The system is trained on 680 000 hours of speech data from the network and recognizes 99 languages.

I generated images from texts using Replicate. Replicate runs machine learning models on the cloud. They have a library of open-source models that we can run with a few lines of code.

To get started.

       Clone the repository

       git clone https://github.com/Ashot72/Speech-to-Text-to-Image
       cd Speech-to-Text-to-Image

       Add your keys to .env file
       
       # installs dependencies
       npm install

       # to run locally
        npm start
      

Go to Speech To Text to Image Generation Video page

Go to Speech To Text to Image Generation description page

speech-to-text-to-image's Issues

showing 401 error

Microsoft Windows [Version 10.0.22631.3155]
(c) Microsoft Corporation. All rights reserved.

C:\Users\rukmi>cd Speech-to-Text-to-Image

C:\Users\rukmi\Speech-to-Text-to-Image>npm start

[email protected] start
ts-node -r dotenv/config index.ts

App listening at http://localhost:3000
C:\Users\rukmi\Speech-to-Text-to-Image\node_modules\axios\lib\core\createError.js:16
var error = new Error(message);
^
Error: Request failed with status code 401
at createError (C:\Users\rukmi\Speech-to-Text-to-Image\node_modules\axios\lib\core\createError.js:16:15)
at settle (C:\Users\rukmi\Speech-to-Text-to-Image\node_modules\axios\lib\core\settle.js:17:12)
at IncomingMessage.handleStreamEnd (C:\Users\rukmi\Speech-to-Text-to-Image\node_modules\axios\lib\adapters\http.js:322:11)
at IncomingMessage.emit (node:events:530:35)
at IncomingMessage.emit (node:domain:488:12)
at endReadableNT (node:internal/streams/readable:1696:12)
at processTicksAndRejections (node:internal/process/task_queues:82:21) {
config: {
transitional: {
silentJSONParsing: true,
forcedJSONParsing: true,
clarifyTimeoutError: false
},
adapter: [Function: httpAdapter],
transformRequest: [ [Function: transformRequest] ],
transformResponse: [ [Function: transformResponse] ],
timeout: 0,
xsrfCookieName: 'XSRF-TOKEN',
xsrfHeaderName: 'X-XSRF-TOKEN',
maxContentLength: -1,
maxBodyLength: -1,
validateStatus: [Function: validateStatus],
headers: {
Accept: 'application/json, text/plain, /',
'Content-Type': 'multipart/form-data; boundary=--------------------------603685013536462814738367',
'User-Agent': 'OpenAI/NodeJS/3.2.1',
Authorization: 'Bearer sk-YUqD8BTx5PMWc0YyzUQaT3Blbk111111111111'
},
method: 'post',
data: FormData {
_overheadLength: 263,
_valueLength: 9,
_valuesToMeasure: [Array],
writable: false,
readable: true,
dataSize: 0,
maxDataSize: 2097152,
pauseStreams: true,
_released: true,
_streams: [],
_currentStream: null,
_insideLoop: false,
_pendingNext: false,
_boundary: '--------------------------603685013536462814738367',
_events: [Object: null prototype],
_eventsCount: 1
},
url: 'https://api.openai.com/v1/audio/transcriptions'
},
request: <ref *1> ClientRequest {
_events: [Object: null prototype] {
abort: [Function (anonymous)],
aborted: [Function (anonymous)],
connect: [Function (anonymous)],
error: [Function (anonymous)],
socket: [Function (anonymous)],
timeout: [Function (anonymous)],
finish: [Function: requestOnFinish]
},
_eventsCount: 7,
_maxListeners: undefined,
outputData: [],
outputSize: 0,
writable: true,
destroyed: true,
_last: false,
chunkedEncoding: true,
shouldKeepAlive: true,
maxRequestsOnConnectionReached: false,
_defaultKeepAlive: true,
useChunkedEncodingByDefault: true,
sendDate: false,
_removedConnection: false,
_removedContLen: false,
_removedTE: false,
strictContentLength: false,
_contentLength: null,
_hasBody: true,
_trailer: '',
finished: true,
_headerSent: true,
_closed: true,
socket: TLSSocket {
_tlsOptions: [Object],
_secureEstablished: true,
_securePending: false,
_newSessionPending: false,
_controlReleased: true,
secureConnecting: false,
_SNICallback: null,
servername: 'api.openai.com',
alpnProtocol: false,
authorized: true,
authorizationError: null,
encrypted: true,
_events: [Object: null prototype],
_eventsCount: 9,
connecting: false,
_hadError: false,
_parent: null,
_host: 'api.openai.com',
_closeAfterHandlingError: false,
_readableState: [ReadableState],
_writableState: [WritableState],
allowHalfOpen: false,
_maxListeners: undefined,
_sockname: null,
_pendingData: null,
_pendingEncoding: '',
server: undefined,
_server: null,
ssl: [TLSWrap],
_requestCert: true,
_rejectUnauthorized: true,
timeout: 5000,
parser: null,
_httpMessage: null,
autoSelectFamilyAttemptedAddresses: [Array],
[Symbol(alpncallback)]: null,
[Symbol(res)]: [TLSWrap],
[Symbol(verified)]: true,
[Symbol(pendingSession)]: null,
[Symbol(async_id_symbol)]: -1,
[Symbol(kHandle)]: [TLSWrap],
[Symbol(lastWriteQueueSize)]: 0,
[Symbol(timeout)]: [Timeout],
[Symbol(kBuffer)]: null,
[Symbol(kBufferCb)]: null,
[Symbol(kBufferGen)]: null,
[Symbol(shapeMode)]: true,
[Symbol(kCapture)]: false,
[Symbol(kSetNoDelay)]: false,
[Symbol(kSetKeepAlive)]: true,
[Symbol(kSetKeepAliveInitialDelay)]: 1,
[Symbol(kBytesRead)]: 0,
[Symbol(kBytesWritten)]: 0,
[Symbol(connect-options)]: [Object]
},
_header: 'POST /v1/audio/transcriptions HTTP/1.1\r\n' +
'Accept: application/json, text/plain, /\r\n' +
'Content-Type: multipart/form-data; boundary=--------------------------603685013536462814738367\r\n' +
'User-Agent: OpenAI/NodeJS/3.2.1\r\n' +
'Authorization: Bearer sk-YUqD8BTx5PMWc0YyzUQaT3Blbk111111111111\r\n' +
'Host: api.openai.com\r\n' +
'Connection: keep-alive\r\n' +
'Transfer-Encoding: chunked\r\n' +
'\r\n',
_keepAliveTimeout: 0,
_onPendingData: [Function: nop],
agent: Agent {
_events: [Object: null prototype],
_eventsCount: 2,
_maxListeners: undefined,
defaultPort: 443,
protocol: 'https:',
options: [Object: null prototype],
requests: [Object: null prototype] {},
sockets: [Object: null prototype] {},
freeSockets: [Object: null prototype],
keepAliveMsecs: 1000,
keepAlive: true,
maxSockets: Infinity,
maxFreeSockets: 256,
scheduling: 'lifo',
maxTotalSockets: Infinity,
totalSocketCount: 1,
maxCachedSessions: 100,
_sessionCache: [Object],
[Symbol(shapeMode)]: false,
[Symbol(kCapture)]: false
},
socketPath: undefined,
method: 'POST',
maxHeaderSize: undefined,
insecureHTTPParser: undefined,
joinDuplicateHeaders: undefined,
path: '/v1/audio/transcriptions',
_ended: true,
res: IncomingMessage {
_events: [Object],
_readableState: [ReadableState],
_maxListeners: undefined,
socket: null,
httpVersionMajor: 1,
httpVersionMinor: 1,
httpVersion: '1.1',
complete: true,
rawHeaders: [Array],
rawTrailers: [],
joinDuplicateHeaders: undefined,
aborted: false,
upgrade: false,
url: '',
method: null,
statusCode: 401,
statusMessage: 'Unauthorized',
client: [TLSSocket],
_consuming: false,
_dumped: false,
req: [Circular *1],
_eventsCount: 4,
responseUrl: 'https://api.openai.com/v1/audio/transcriptions',
redirects: [],
[Symbol(shapeMode)]: true,
[Symbol(kCapture)]: false,
[Symbol(kHeaders)]: [Object],
[Symbol(kHeadersCount)]: 26,
[Symbol(kTrailers)]: null,
[Symbol(kTrailersCount)]: 0
},
aborted: false,
timeoutCb: null,
upgradeOrConnect: false,
parser: null,
maxHeadersCount: null,
reusedSocket: false,
host: 'api.openai.com',
protocol: 'https:',
_redirectable: Writable {
_events: [Object],
_writableState: [WritableState],
_maxListeners: undefined,
_options: [Object],
_ended: true,
_ending: true,
_redirectCount: 0,
_redirects: [],
_requestBodyLength: 50044,
_requestBodyBuffers: [],
_eventsCount: 3,
_onNativeResponse: [Function (anonymous)],
_currentRequest: [Circular *1],
_currentUrl: 'https://api.openai.com/v1/audio/transcriptions',
[Symbol(shapeMode)]: true,
[Symbol(kCapture)]: false
},
[Symbol(shapeMode)]: false,
[Symbol(kCapture)]: false,
[Symbol(kBytesWritten)]: 0,
[Symbol(kNeedDrain)]: true,
[Symbol(corked)]: 0,
[Symbol(kOutHeaders)]: [Object: null prototype] {
accept: [Array],
'content-type': [Array],
'user-agent': [Array],
authorization: [Array],
host: [Array]
},
[Symbol(errored)]: null,
[Symbol(kHighWaterMark)]: 16384,
[Symbol(kRejectNonStandardBodyWrites)]: false,
[Symbol(kUniqueHeaders)]: null
},
response: {
status: 401,
statusText: 'Unauthorized',
headers: {
date: 'Fri, 01 Mar 2024 16:04:31 GMT',
'content-type': 'application/json; charset=utf-8',
'content-length': '291',
connection: 'keep-alive',
vary: 'Origin',
'x-request-id': 'req_520720ec1c6057ec643d27dae6d89cf9',
'strict-transport-security': 'max-age=15724800; includeSubDomains',
'cf-cache-status': 'DYNAMIC',
'set-cookie': [Array],
server: 'cloudflare',
'cf-ray': '85da621ef9f92e8a-HYD',
'alt-svc': 'h3=":443"; ma=86400'
},
config: {
transitional: [Object],
adapter: [Function: httpAdapter],
transformRequest: [Array],
transformResponse: [Array],
timeout: 0,
xsrfCookieName: 'XSRF-TOKEN',
xsrfHeaderName: 'X-XSRF-TOKEN',
maxContentLength: -1,
maxBodyLength: -1,
validateStatus: [Function: validateStatus],
headers: [Object],
method: 'post',
data: [FormData],
url: 'https://api.openai.com/v1/audio/transcriptions'
},
request: <ref *1> ClientRequest {
_events: [Object: null prototype],
_eventsCount: 7,
_maxListeners: undefined,
outputData: [],
outputSize: 0,
writable: true,
destroyed: true,
_last: false,
chunkedEncoding: true,
shouldKeepAlive: true,
maxRequestsOnConnectionReached: false,
_defaultKeepAlive: true,
useChunkedEncodingByDefault: true,
sendDate: false,
_removedConnection: false,
_removedContLen: false,
_removedTE: false,
strictContentLength: false,
_contentLength: null,
_hasBody: true,
_trailer: '',
finished: true,
_headerSent: true,
_closed: true,
socket: [TLSSocket],
_header: 'POST /v1/audio/transcriptions HTTP/1.1\r\n' +
'Accept: application/json, text/plain, /\r\n' +
'Content-Type: multipart/form-data; boundary=--------------------------603685013536462814738367\r\n' +
'User-Agent: OpenAI/NodeJS/3.2.1\r\n' +
'Authorization: Bearer sk-YUqD8BTx5PMWc0YyzUQaT3Blbk111111111111\r\n' +
'Host: api.openai.com\r\n' +
'Connection: keep-alive\r\n' +
'Transfer-Encoding: chunked\r\n' +
'\r\n',
_keepAliveTimeout: 0,
_onPendingData: [Function: nop],
agent: [Agent],
socketPath: undefined,
method: 'POST',
maxHeaderSize: undefined,
insecureHTTPParser: undefined,
joinDuplicateHeaders: undefined,
path: '/v1/audio/transcriptions',
_ended: true,
res: [IncomingMessage],
aborted: false,
timeoutCb: null,
upgradeOrConnect: false,
parser: null,
maxHeadersCount: null,
reusedSocket: false,
host: 'api.openai.com',
protocol: 'https:',
_redirectable: [Writable],
[Symbol(shapeMode)]: false,
[Symbol(kCapture)]: false,
[Symbol(kBytesWritten)]: 0,
[Symbol(kNeedDrain)]: true,
[Symbol(corked)]: 0,
[Symbol(kOutHeaders)]: [Object: null prototype],
[Symbol(errored)]: null,
[Symbol(kHighWaterMark)]: 16384,
[Symbol(kRejectNonStandardBodyWrites)]: false,
[Symbol(kUniqueHeaders)]: null
},
data: { error: [Object] }
},
isAxiosError: true,
toJSON: [Function: toJSON]
}