Agent Integrations

Sarvam text-to-speech (Bulbul) for 11 Indian languages

Synthesizes speech and returns base64 audio in audios. Billed per character of text at Sarvam's list price (₹30 per 10,000 characters, converted at SARVAM_INR_PER_USD) plus AGENT_INTEGRATION_SARVAM_MARGIN. The response is Sarvam's plus characters and costUsd.

post/agent-integrations/sarvam/text-to-speech

Request

  • Base URL: https://api.tinyhumans.ai
  • URL: https://api.tinyhumans.ai/agent-integrations/sarvam/text-to-speech
  • Auth: HTTP bearer

Request body

textstring required

At most 2500 characters on bulbul:v3, 1500 on bulbul:v2

language_code'bn-IN' | 'en-IN' | 'gu-IN' | 'hi-IN' | 'kn-IN' | 'ml-IN' | 'mr-IN' | 'od-IN' | 'pa-IN' | 'ta-IN' | 'te-IN' required
model'bulbul:v3' | 'bulbul:v2'
speakerstring

Lowercase Sarvam voice name (e.g. shubh)

pacenumber
temperaturenumber

bulbul:v3 only

pitchnumber

bulbul:v2 only

loudnessnumber

bulbul:v2 only

speech_sample_rate8000 | 16000 | 22050 | 24000 | 32000 | 44100 | 48000
output_audio_codec'wav' | 'mp3' | 'linear16' | 'mulaw' | 'alaw' | 'opus' | 'flac' | 'aac'
enable_preprocessingboolean
dict_idstring

Response

Base64 audio (audios, request_id) plus characters and costUsd

Changes

No recorded changes to this operation across all 1 revision of this API.