Speech synthesis APIs
Explore speech synthesis models for voice agents, narration, accessibility, and conversational products. Per-character and per-minute rates remain separate comparison groups.
Current catalog
3
text-to-speech models with verified catalog metadata
Pricing content refreshed July 25, 2026
Currently the lowest-priced option in the provider price per one million characters group. Different billing units are never mixed.
$0.180 / 1M characters
View pricing and providersComparable models are ordered by their current normalized price.
3 models
sarvam
Bulbul v2 is a high-speed, cost-effective TTS model supporting 11 Indian languages. It is distinguished by its 'Just Like India' authentic regional accents and offers granular control over pitch, speed, and volume. Optimized for real-time synthesis in customer service and e-learning applications.
Price
$0.180 / 1M characters
Context
2000
sarvam
Bulbul v3 is a production-grade text-to-speech model optimized for 11 Indian languages. It features native support for code-mixed speech, professional voice cloning, and industry-leading stability in telephony environments (8 kHz). It automatically infers prosody, emphasis, and emotional tone.
Price
$0.350 / 1M characters
Context
2000
cc94bcd3662444fb92e43506c7036c08
Speech 2.8-turbo is a text-to-speech model
Price
See providers
Context
2K
OneInfer compares only positive prices with the same billing unit. Per-minute, per-character, per-token, per-image, per-video, and per-second rates remain separate. Prices can change, so the current model page and console remain the source of truth.
OneInfer compares models only when they use the same billing unit, such as price per million characters. Different units are not combined into a misleading ranking.
No. Voice cloning is shown only when it is explicitly provided in verified model metadata.