Text-to-speech API · served now

Piper API — EU text-to-speech

A European TTS API: Piper behind the OpenAI-compatible /v1/audio/speech endpoint, served from hardware AxForge owns in Sweden. Fast CPU synthesis, zero prompt retention.

eu-se-1 · Stockholm api.axforge.ai/v1 €2.95 / 1M characters
Get an API key Talk to an engineer Keys are allocated from the waiting list.

Specifications

What is served

ModelPiper — text-to-speech, fast CPU synthesis
API model namepiper
EndpointPOST /v1/audio/speech
ComputeCPU — synthesis does not queue behind GPU inference
HardwareSystems owned and operated by AxForge in Sweden
Regioneu-se-1 · Stockholm, Sweden — pinned with x-axforge-region, echoed on the response
Pricing€2.95 / 1M characters (launch pricing)

For quality samples, see the official model card — we publish only numbers we measured ourselves.

Quickstart

OpenAI-compatible — text in, audio out

curl
$ export OPENAI_BASE_URL=https://api.axforge.ai/v1
$ curl -sS "$OPENAI_BASE_URL/audio/speech" \
    -H "Authorization: Bearer $AXFORGE_API_KEY" \
    -H "x-axforge-region: eu-se-1" \
    -H "Content-Type: application/json" \
    -d '{"model":"piper","voice":"<voice-id>",
         "input":"Synthesized in Stockholm, retained nowhere."}' \
    --output speech.wav
Python
# pip install openai
from openai import OpenAI

client = OpenAI(
    base_url="https://api.axforge.ai/v1",
    api_key="YOUR_AXFORGE_KEY",
    default_headers={"x-axforge-region": "eu-se-1"},
)
r = client.audio.speech.create(
    model="piper",
    voice="<voice-id>",
    input="Synthesized in Stockholm, retained nowhere.",
)
r.write_to_file("speech.wav")

Data & privacy

Zero prompt retention

Prompts and completions are processed in memory in Sweden — not written to disk, not logged, not retained, and never used to train anything. For this endpoint that means the text you send and the audio we return. We keep only request metadata (token counts, timestamps, status) for billing and operations. The full policy is at axforge.ai/privacy.

FAQ

Piper API — common questions

Is the Piper API OpenAI-compatible?

Yes. It is the standard /v1/audio/speech shape at https://api.axforge.ai/v1, with the model name piper, so the official OpenAI SDKs work by changing base_url.

Why a CPU text-to-speech model?

Piper is a fast CPU synthesizer. Synthesis does not queue behind GPU inference workloads, which keeps text-to-speech a lightweight, always-available endpoint.

Where is the TTS API hosted?

In Stockholm, Sweden (region eu-se-1), on hardware AxForge owns and operates. TLS terminates in the EU. Spain (eu-es-1) is live for the platform; more EU regions are in deployment.

Is the text I synthesize stored?

No. Requests are processed in memory under our zero-retention policy — the text you send and the audio we return are not written to disk, not logged, not retained, and never used for training. See the privacy policy.

What does the text-to-speech API cost?

€2.95 per million characters (launch pricing). For committed volume, talk to an engineer.

Ready to build on EU inference?

Get an API key Talk to an engineer

Explore

All models

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms