eroq api · voice
Give it a voice.
Then get it back.
Two speech models at two to three credits per hundred characters, a curated roster, and cloning from a clean recording. Assign a voice to a character and every line they speak is the same voice — then transcribe audio back to text on the same key.
MP3 out · 13 languages · clones private to your account
50 free credits on signup · no card required
curl https://eroq.ai/v1/audio/speech \
-H "Authorization: Bearer $EROQ_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "eroq-voice-one",
"input": "That noise is the reactor missing its coolant flush. Again.",
"voice": "aria"
}' \
--output speech.mp3The models
3 models. Flat prices.
Voice One
speecheroq-voice-one
Natural speech synthesis with a curated voice roster. Returns MP3 audio directly.
3 credits / 100 characters
Voice Turbo
speecheroq-voice-turbo
The high-volume voice tier: lower latency and a lower price, same roster and cloned voices as Voice One.
2 credits / 100 characters
Scribe One
transcriptioneroq-scribe-one
Transcription with automatic language detection, built for voice-message-length audio.
5 credits / request
What you get
Voice, built for products that ship.
Two speeds
Voice One at three credits per hundred characters, Voice Turbo at two. Same request shape and the same roster — Turbo trades a little nuance for latency and cost when the line is a notification rather than a performance.
Clone a voice
Upload a clean recording and the clone is yours alone — private to your account, usable from the API, the studio and any character you assign it to. It is not published to a shared roster and no one else can reach it.
Characters that speak
Bind a voice to a saved character and every line they say comes out in it, whether the call comes from your product, a film or the studio. One assignment rather than a voice id threaded through every call site.
Direction by punctuation
Speed and expressiveness are parameters, and the rest of the performance is punctuation — the engines respond to commas, ellipses and line breaks. There is no SSML dialect to learn and none to get wrong.
Thirteen languages
The same voices speak thirteen languages, so a cloned narrator can read copy that was never recorded in that language. Pronunciation follows the text, so numbers and names are worth spelling out.
And back again
Transcription runs on the same key at five credits a request, which closes the loop for captioning your own narration. There is no speaker diarization and no word-level timestamps, so it returns text, not a subtitle file.
In the reference
Keep reading
FAQ
The short version.
What does speech cost? +
Three credits per hundred characters on Voice One and two on Voice Turbo, billed on the text you send. Transcription is five credits a request.
Who can use a voice I clone? +
Only your account. Clones are private, are not added to any shared roster, and can be deleted, which removes them from every character they were assigned to.
What format comes back? +
MP3. There is no streaming audio endpoint, so a long passage arrives as one finished file rather than as it is spoken.
Can it lip-sync to a generated face? +
No. Speech and video are separate calls and there is no lip-sync tool. Veo 3 Fast can render a spoken line as part of a clip, but you cannot lay a voice track over an existing clip and have the mouth match.
Does transcription return timestamps? +
No — it returns text. There is no diarization, no word-level timing and no subtitle file, so captions still need a pass in your editor.
First call in five minutes.
Sign up, create a key, paste the quickstart. 50 free credits are enough to try every model, and plans start at $15.