Amazon Nova SonicSpeech-to-speech
amazon.nova-2-5-sonic
Amazon's latest speech-to-speech foundation model on Bedrock, with improved reasoning, instruction following and tool calling over Nova 2 Sonic, plus lower latency.
01 Price
$3.00per 1M tokens
| Plan or mode | Price |
|---|---|
| speech_output | $12.00 per 1M tokens |
| text_input | $0.33 per 1M tokens |
| text_output | $2.75 per 1M tokens |
On-demand Standard tier, US East (N. Virginia): speech input $0.003, speech output $0.012, text input $0.00033, text output $0.00275 per 1K tokens ($3 / $12 / $0.33 / $2.75 per 1M), converted to per-token. Amounts read from the AWS Price List API (AmazonBedrock offer, us-east-1) as the pricing page renders tables client-side.
Pricing source, checked 2026-11-18
02 Languages many
Many languages. Amazon Nova Sonic doesn't list them individually.
03 Features 0 of 19 listed
- Word timestampsnot listed
- Speaker diarizationnot listed
- Punctuationnot listed
- Profanity filternot listed
- Custom vocabularynot listed
- Language detectionnot listed
- Translationnot listed
- Sentimentnot listed
- PII redactionnot listed
- Summarizationnot listed
- Topic detectionnot listed
- Emotion controlnot listed
- Voice cloningnot listed
- Voice designnot listed
- SSMLnot listed
- Phoneme inputnot listed
- Speed / prosody controlnot listed
- Style controlnot listed
- Multi-speakernot listed
"Not listed" means the provider's data doesn't mention it, not that the model lacks it.
04 Get this record
curl https://voicedex.dev/v1/providers/amazon-nova/models/amazon.nova-2-5-sonic
Free, no key needed. Use model id amazon.nova-2-5-sonic with Amazon Nova Sonic's own API. API reference.