feather and starling run on ordinary CPUs, so speech and voice cloning go where GPUs can't: every cloud region, your own datacenter, air-gapped, wherever your data has to stay. From $1.90 per million characters, a fraction of GPU-bound APIs.
Same OpenAI-compatible endpoint, two very different price-performance points. Mix them per request: feather for the high-volume paths, starling where the voice IS the product.
A single clone, or any preset voice, speaks every language below, including scripts the original speaker never learned. Every major Indian language is covered.
starling builds a production-ready clone from half a minute of clean audio: your brand ambassador, your founder, your support lead. The clone speaks all 107 languages, even ones the speaker never learned.
Record 30 seconds. A phone memo is enough; a quiet room is better.
Upload once. The clone is frozen as a private voice on your account.
Speak everywhere. Same voice, any script, any of 107 languages, via one API call.
Real products aren't used in a silent booth. starling can place a voice inside a room, a cafe, a call floor, a moving street, so agents, IVR, and announcements sound like they belong there. One request parameter, no post-production. Press play on any room.
One OpenAI-compatible call. Sentences stream while the rest is still being synthesised, so voice agents answer like people, not like voicemail. 382 ms to the first word; 6.1× faster than playback for everything after it.
Each row is a real recording of the same line from that provider's model. The meters count up in lockstep with playback: each number is that model's price per million characters, not the cost of this clip.
FIG. 01 · seven engines, published list prices per 1M characters, each paired with the model you hear.
Published list prices per 1M characters · verified June 2026
feather and starling run on ordinary CPUs, so they go everywhere CPUs already are: every cloud region on earth, your own datacenter, even air-gapped. The GPUs behind frontier AI don't. That gap is your data-residency story, and a moat GPU-bound vendors can't cross.
Every major cloud offers general-purpose CPUs in 100% of its regions. The H100 and A100 GPUs behind frontier models reach only a fraction, so a GPU-bound vendor cannot serve customers whose data has to stay in the other two-thirds.
Total regions versus H100 and A100 availability, mid-2026. Even counting every inference GPU (T4, L4, A10G), coverage stays partial: roughly 64% of AWS regions, 40% of Azure, 77% of GCP. CPUs are in 100% of all three. Sources: AWS, Azure, Google Cloud.
No rented GPUs in the path, so the rates hold in every cloud region, on-premise, and air-gapped.