API Guides & TutorialsText to SpeechHow-to

How to change the speaker voice

The speaker parameter lets you choose a specific voice for the speech output.

Speaker names are case-sensitive and must be lowercase (e.g., shubh, not Shubh).

Speaker Selection

Specify the speaker using the speaker parameter in your request. It is an optional parameter — if omitted, the API uses the default voice (shubh for bulbul:v3, anushka for bulbul:v2).

Available Voices — Bulbul v3

Bulbul v3 offers 30+ natural-sounding voices:

Male: shubh (default), aditya, rahul, rohan, amit, dev, ratan, varun, manan, sumit, kabir, aayan, ashutosh, advait, anand, tarun, sunny, mani, gokul, vijay, mohit, rehan, soham

Female: ritu, priya, neha, pooja, simran, kavya, ishita, shreya, roopa, amelia, sophia, tanya, shruti, suhani, kavitha, rupali

Speakers are evaluated by Critical Error Rate (CER) — the percentage of words with critical pronunciation errors. Lower CER = higher reliability.

TierCER RangeRecommendation
Tier 1 — Excellent≤ 0.20%First choice for all production use
Tier 2 — Good0.21–0.40%Safe for production use
Tier 3 — Moderate0.41–0.60%Acceptable; test per language before deploying
SpeakerGenderCERQuality Tier
maniMale0.00%Tier 1 — Excellent
priyaFemale0.13%Tier 1 — Excellent
ishitaFemale0.13%Tier 1 — Excellent
varunMale0.06%Tier 1 — Special Use ★
roopaFemale0.26%Tier 2 — Good
shubhMale0.30%Tier 2 — Good
poojaFemale0.30%Tier 2 — Good
sunnyMale0.33%Tier 2 — Good
ratanMale0.33%Tier 2 — Good
rehanMale0.33%Tier 2 — Good
ashutoshMale0.40%Tier 2 — Good
amitMale0.40%Tier 2 — Good
rahulMale0.40%Tier 2 — Good
adityaMale0.46%Tier 3 — Moderate
simranFemale0.46%Tier 3 — Moderate
suhaniFemale0.46%Tier 3 — Moderate
shreyaFemale0.46%Tier 3 — Moderate
anandMale0.46%Tier 3 — Moderate
rupaliFemale0.50%Tier 3 — Moderate
nehaFemale0.53%Tier 3 — Moderate
rituFemale0.53%Tier 3 — Moderate
mananMale0.53%Tier 3 — Moderate
devMale0.60%Tier 3 — Moderate

★ Note on varun: Despite having a very low CER (0.06%), varun carries a deep, dramatic villain/suspense character. He is not suitable as a neutral default. Reserve varun exclusively for thriller, drama, or suspense content.

Not all speakers perform equally across all languages. Always use these language-specific picks over arbitrary selection:

LanguageCodeRecommended MaleRecommended Female
Englishen-INratanishita
Hindihi-INshubh, ashutoshpriya, suhani
Telugute-INshubh, ratanneha, priya
Kannadakn-INshubh, ratanneha, ishita
Bengalibn-INrehanroopa, suhani
Tamilta-INratan, rohanishita, ritu
Odiaod-INshubhritu, pooja
Malayalamml-INshubhpooja
Marathimr-INratanpriya, ritu
Punjabipa-INmaniroopa, suhani
Gujaratigu-INratanpriya, ritu

Top picks: priya & ishita (best female — use across Hindi, Telugu, Kannada, Tamil, Marathi, Gujarati, English) · mani (best male overall, Punjabi) · shubh (best male for hi, te, kn, od, ml) · ratan (best male for en, te, kn, ta, mr, gu).

Available Voices — Bulbul v2

Female Voices

  • anushka: Clear and professional
  • manisha: Warm and friendly
  • vidya: Articulate and precise
  • arya: Young and energetic

Male Voices

  • abhilash: Deep and authoritative
  • karun: Natural and conversational
  • hitesh: Professional and engaging

Listen to voice samples on our dashboard: Voice Samples – Sarvam TTS

Example Code

1from sarvamai import SarvamAI
2from sarvamai.play import save
3
4# Initialize the REST client
5client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY")
6
7# Generate speech using REST
8audio = client.text_to_speech.convert(
9    text="Welcome to Sarvam AI!",
10    model="bulbul:v3",
11    target_language_code="en-IN",
12    speaker="shubh"
13)
14save(audio, "output1.wav")