Best Practice Guide for Bulbul v4 Flash

Bulbul v4 Flash is Sarvam’s low-latency TTS tier for interactive workloads: voice agents, IVR, and anything where a listener is waiting for the first word. This guide applies only to model="bulbul:v4-flash" with persona speaker IDs (voice_language_style). For the stable bulbul:v3 model (short names like shubh, priya), see Bulbul v3 best practices.

What is Bulbul v4 Flash?

Flash is the interactive tier of the v4 family. It runs on production infrastructure and is available over three transports (HTTP streaming, single-response REST, and WebSocket) so you can match your pipeline instead of forcing one mode.

Choosing the right endpoint

All transports serve the same model; they differ in latency, max sample rate, and how audio is delivered.

Reuse connections: Each new HTTPS connection pays DNS, TCP, and TLS before any audio work. Enable keep-alive or pool clients so one connection serves many synthesis calls.

See also Which API to Use.

Quick start

HTTP streaming

{
  "text": "नमस्ते! आपका order 2 दिन में deliver हो जाएगा।",
  "language_code": "hi-IN",
  "model": "bulbul:v4-flash",
  "speaker": "aparna_hi_customer",
  "speech_sample_rate": 24000,
  "output_audio_codec": "wav",
  "pace": 1.0,
  "enable_preprocessing": true
}

POST https://api.sarvam.ai/text-to-speech/stream with header api-subscription-key.

WebSocket

Connect to wss://api.sarvam.ai/text-to-speech/ws?model=bulbul:v4-flash with api-subscription-key on the upgrade request. Per utterance, send in order:

{"type": "config", "data": {
  "speaker": "aparna_hi_customer",
  "language_code": "hi-IN",
  "speech_sample_rate": 24000,
  "output_audio_codec": "wav",
  "pace": 1.0
}}

{"type": "text", "data": {"text": "नमस्ते! मैं आपकी कैसे मदद कर सकती हूँ?"}}

{"type": "flush"}

Audio arrives as {"type":"audio"} messages with base64 in data.audio. Hold the socket open across many calls; send {"type":"ping"} on idle links.

Parameter reference (v4 Flash)

Values outside allowed ranges return 400. Validate in your client to avoid wasted round trips on live calls.

Tuning guidance

Writing text for natural speech

Input formatting affects perceived quality more than parameter tweaks. Most early issues trace back to this section.

Punctuation for pauses

Fillers and code-mixing

For conversational Hinglish, write English in Latin script and Indic words in native script, as a bilingual reader would:

• "आपका order confirm हो गया है"
• "Aapka order confirm ho gaya hai"

Use _enhi_ personas (simran_enhi_customer, ishita_enhi_customer, shubh_enhi_banking, …) when copy is genuinely mixed English–Hindi in one utterance, not just a few loan words.

Write each language in its own script

Romanised Hindi/Tamil/etc. degrades quality — the model was trained on native scripts.

Let preprocessing handle numbers

With enable_preprocessing: true, do not hand-expand numbers, dates, or currency into words — you will usually get a worse reading than the model’s language-specific rules.

Chunk on sentence boundaries

Split long or LLM-generated text at sentence boundaries. Mid-sentence splits strand intonation and sound like an audible seam. Buffer LLM tokens until you have a full sentence, then synthesise.

Match voice to language

Personas are not equally strong in all eleven languages. Use the rankings below and audition cross-language use before production.

Avoid

Target language code

language_code is required. It drives number, date, and entity reading rules.

audio = client.text_to_speech.convert(
    text="नमस्ते! Sarvam AI में आपका स्वागत है।",
    model="bulbul:v4-flash",
    language_code="hi-IN",
    speaker="aparna_hi_customer",
)

Speaker ID format

Every v4 Flash ID follows voice_language_style:

The same voice can appear under multiple styles (ritu_hi_customer vs ritu_hi_reels) with different energy — switching style is often better than switching voice.

Recommended voices by use case

Expert picks for English (en-IN) and Hindi (hi-IN). Treat rank 1 as default; ranks 2–3 are A/B candidates. The full roster is browsable on Voices; the style segment (customer, recovery, sales, …) is a reliable guide when your use case is not listed.

English (en-IN)

Hindi (hi-IN)

Roster coverage by language

Decoding API audio (base64)

REST returns base64 in the audios array. Decode before writing to disk.

import base64
from sarvamai import SarvamAI
client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY")
audio = client.text_to_speech.convert(
    text="नमस्ते! Sarvam AI में आपका स्वागत है।",
    model="bulbul:v4-flash",
    language_code="hi-IN",
    speaker="aparna_hi_customer",
)
audio_bytes = base64.b64decode("".join(audio.audios))
with open("output.wav", "wb") as f:
    f.write(audio_bytes)

For WebSocket streaming, decode each chunk as it arrives. See WebSocket streaming.

Output formats and sample rates

Handling errors

On WebSocket, errors often arrive as {"type":"error"} followed by a close — reconnect before retrying.

Log request_id from responses when debugging with support.

WebSocket connection management

• Idle timeout: connections close after prolonged inactivity — send ping well before that window.
• Pronunciations: use a pronunciation dictionary for names and brands instead of phonetic spelling hacks.

Key considerations

• For large numbers, use grouping that matches your locale (e.g. 10,000 or 5,00,000) so preprocessing reads them correctly.
• v4 Flash does not support SSML — use pace, pitch, loudness, and sentence-boundary chunking for rhythm.
• Character limits apply per request/session (typically 2,500) — chunk at sentences.

Quick reference

Need bulbul:v3 short-name speakers or temperature tuning? See Bulbul v3 best practices.