Text to Speech & Transcription

Text to Speech & Transcription

Generates audio from text using a specified voice

post
Authorizations
X-API-KeystringRequired
Header parameters
X-API-KeystringRequired

Your API key

Body
textstringRequired

Text to convert to speech

vibestring · enumOptional

Optional vibe

Possible values:
voicestring · enumOptional

Base voice

Default: alloyPossible values:
Responses
200

Success

No content

post
/generate-audio/generate
200

Success

No content

Transcribes an uploaded audio file (auto-detects format)

post
Authorizations
X-API-KeystringRequired
Header parameters
X-API-KeystringRequired

Your API key

X-Fieldsstring · maskOptional

An optional fields mask

Body
audio_filestring · binaryRequired

Audio file to transcribe. Format will be auto-detected.

Responses
200

Success

application/json
post
/generate-audio/transcribe-file

Transcribes audio from a URL (downloads, auto-detects format)

post
Authorizations
X-API-KeystringRequired
Header parameters
X-API-KeystringRequired

Your API key

X-Fieldsstring · maskOptional

An optional fields mask

Body
audio_urlstringRequired

URL of the audio file to transcribe (e.g., mp3, wav). Format auto-detected.

Responses
200

Success

application/json
post
/generate-audio/transcribe-url

List available voice options for text-to-speech generation

get

Lists the available voice options for audio generation.

Responses
200

Success

No content

get
/generate-audio/voices
200

Success

No content

Last updated