curl --request POST \
--url https://api.slng.ai/v1/tts/sarvam/bulbul-stream:v3 \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"text": "Hello, this is a streamed Sarvam synthesis request.",
"target_language_code": "en-IN",
"speaker": "shubh",
"model": "bulbul:v3",
"output_audio_codec": "mp3"
}
'"<string>"{
"error": "Validation error",
"details": "Missing required field: text"
}{
"error": "TTS service error",
"status": 400,
"details": "Rime TTS API error: 400 Bad Request - Invalid argument: Invalid speaker: aurelie"
}{
"error": "Service error",
"details": "Internal processing error"
}{
"error": "TTS service error",
"status": 400,
"details": "Rime TTS API error: 400 Bad Request - Invalid argument: Invalid speaker: aurelie"
}Sarvam AI Bulbul Stream v3
Bulbul Stream v3
HTTP-streaming multilingual TTS for Indian languages with 30+ speaker voices. Returns raw audio bytes (chunked) in the codec selected via output_audio_codec. Unlike sarvam/bulbul:v3, no X-Duration header is sent and no JSON envelope is used.
POST
/
v1
/
tts
/
sarvam
/
bulbul-stream:v3
curl --request POST \
--url https://api.slng.ai/v1/tts/sarvam/bulbul-stream:v3 \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"text": "Hello, this is a streamed Sarvam synthesis request.",
"target_language_code": "en-IN",
"speaker": "shubh",
"model": "bulbul:v3",
"output_audio_codec": "mp3"
}
'"<string>"{
"error": "Validation error",
"details": "Missing required field: text"
}{
"error": "TTS service error",
"status": 400,
"details": "Rime TTS API error: 400 Bad Request - Invalid argument: Invalid speaker: aurelie"
}{
"error": "Service error",
"details": "Internal processing error"
}{
"error": "TTS service error",
"status": 400,
"details": "Rime TTS API error: 400 Bad Request - Invalid argument: Invalid speaker: aurelie"
}Authorizations
API key issued by SLNG. Pass as Authorization: Bearer <token>.
Headers
Target world part override. Auto-selected if not provided.
Available options:
in Body
application/json
Sarvam AI Bulbul streaming TTS request.
Text to synthesize. Supports code-mixed text (English and Indic languages).
Required string length:
1 - 3500Language code in BCP-47 format for text normalization.
Available options:
bn-IN, en-IN, gu-IN, hi-IN, kn-IN, ml-IN, mr-IN, od-IN, pa-IN, ta-IN, te-IN Speaker voice for the output audio.
Available options:
shubh, aditya, ritu, priya, neha, rahul, pooja, rohan, simran, kavya, amit, dev, ishita, shreya, ratan, varun, manan, sumit, roopa, kabir, aayan, ashutosh, advait, amelia, sophia, anand, tanya, tarun, sunny, mani, gokul, vijay, shruti, suhani, mohit, kavitha, rehan, soham, rupali Sarvam TTS model identifier.
Available options:
bulbul:v3 Output audio codec. Determines the response Content-Type.
Available options:
mp3, wav, aac, opus, flac, linear16, mulaw, alaw Output audio bitrate.
Available options:
32k, 64k, 128k, 192k, 256k Speech speed (0.5 to 2.0).
Required range:
0.5 <= x <= 2Output sample rate in Hz.
Controls expressiveness (0.01 to 1.0).
Required range:
0.01 <= x <= 1Normalize English words and numbers before synthesis.
Response
Synthesis successful. Returns binary audio in the codec specified by output_audio_codec (chunked stream).
Binary audio data.
Was this page helpful?
⌘I