Speech-to-Text & Text-to-Speech

POST https://api.forii.in/inference/v1/audio/transcriptions

curl https://api.forii.in/inference/v1/audio/transcriptions \
  -H "Authorization: Bearer $FORII_API_KEY" \
  -F file="@recording_hindi.mp3" \
  -F model="forii/saarika-v2" \
  -F language="hi" \
  -F response_format="verbose_json" \
  -F timestamp_granularities[]="word"

POST https://api.forii.in/inference/v1/audio/speech

response = client.audio.speech.create(
    model="forii/bulbul-v2",
    voice="amrita",
    input="नमस्ते, आपका खाता शेष रुपये पाँच हजार है।",
)
response.stream_to_file("output_hindi.mp3")