Bodhi API Platform
Speech infrastructure for Indian languages
Transcribe and synthesize speech across ten Indian languages, in one request or as a live stream. One API key, credits metered per use, no minimum plan.
curl -X POST https://stt.navana.ai/api/transcribe \
-H "X-Api-Key: $BODHI_API_KEY" \
-F "model=hi-banking-v2-8khz" \
-F "transaction_id=$(uuidgen)" \
-F "audio_file=@recording.wav"Capabilities
Speech to Text
Upload a recording and get the whole transcript back, or stream audio over a WebSocket and read partial transcripts as the words are still being spoken.
non-streaming + streaming · 10 languages
Text to Speech
Send a block of text and get the complete audio back, or stream text in and get audio out sentence by sentence while the rest is still being written.
non-streaming + streaming · 10 languages
Why build on it
Indian languages, telephony-first
Models tuned per language for financial-services vocabulary, trained at 8 kHz, the rate real phone calls arrive at.
Built for code-switching
Most models are bilingual with English, because that is how these languages are actually spoken on Indian calls.
One voice across ten languages
A synthesis voice is an identity rather than a recording, so the same voice id reads Hindi, Tamil, or Bengali without a per-language mapping table.
One key, metered per use
One key from the platform authorizes every call, and every call draws down the same credit balance. No per-request fees and no minimum plan.