Get Speech ⚠️

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Bearer token for authentication. Format is 'Bearer {token}'

The text to be synthesized into speech

The ID of the voice to be used for synthesis:

• 'prabhu_indian_male'
• 'vijay_indian_male'
• 'suresh_indian_male'
• 'anuja_indian_female'
• 'govind_indian_male'
• 'anamika_whisper_female'
• 'joy_sleepy_male'
• 'willian_angry_male'
• 'mehul_cheerful_male'
• 'janhvi_professional_female'
• 'chandralekha_bengal_female'
• 'rustom_bengal_male'
• 'rakesh_north_indian_male'
• 'sarika_north_indian_female'
• 'ishwara_south_indian_male'
• 'jatin-mp-male'
• 'kavya-del-female'
• 'anamika-UP-female'
• 'abhay-UP-male'
• 'chandralekha_bengal_female'
• 'rustom_bengal_male'
• 'rakesh_north_indian_male'
• 'sarika_north_indian_female'
• 'ishwara_south_indian_male'

The speed of the speech, ideally between 0.5 and 2

Whether to return the wav file with a header or without a header

Sample rate of the output wav file.

A PCM int16 WAV file at the specified frequency.