How to choose audio formats

Input formats

The file uploaded to POST /voices/create accepts the following codecs:

For best cloning quality, use WAV or FLAC. Telephony codecs (MULAW, ALAW) work but cap the achievable fidelity at the source.

Output formats

One-shot (POST /voices/clone)

Specify the output codec via output_audio_codec. The default is wav.

Streaming (POST /voices/clone/stream and WebSocket)

Streaming endpoints default to mp3 and only accept codecs that concatenate cleanly across sentences:

flac, aac, and opus are rejected on streaming endpoints (422). Optional output_audio_bitrate (32k–192k, default 128k) applies to lossy codecs. See HTTP Streaming.

Sample rate

Use speech_sample_rate to set the output sample rate in Hz:

8000, 16000, 22050, 24000, 32000, 44100, 48000

If omitted, the API returns audio at the model’s native rate (24,000 Hz). Set the sample rate to match your downstream pipeline:

File size guidance

Higher sample rates and uncompressed codecs produce larger output files. As a rough guide for a 10-second clip:

For high-volume API usage, choose a compressed codec (mp3, opus, aac) unless your downstream pipeline specifically requires uncompressed audio.

Decoding the response

The audio field is a base64-encoded string of the raw bytes for the codec you requested. Prefer the SDK — it returns the same payload without hand-building multipart:

import base64
from sarvamai import SarvamAI
client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY")
response = client.voice_cloning.convert(
    voice_id="svc-your-voice-id",
    text="Hello world",
    language_code="en-IN",
    output_audio_codec="wav",
)
with open("output.wav", "wb") as f:
    f.write(base64.b64decode(response.audio))

Next steps