Synthesize speech from text (audio/wav, or base64 JSON)
API · /tts-api
Text-to-Speech API
Convert text into natural-sounding speech audio (WAV) in 30+ languages and voices, with adjustable speaking speed, pitch and amplitude. Returns raw audio/wav or base64-encoded JSON — ideal for voice notifications, accessibility, IVR prompts and audio content generation. Fully self-hosted, no third-party voice service.
API health
healthy- Uptime
- 100.00%
- Server probes · 24h
- Avg latency
- 112 ms
- Server probes · 24h
- Subscribers
- 4,661
- active
- Total calls
- 38
- last 7 days
Pricing
Pick a tier — billed monthly, cancel anytime.
Free
Free
- 1,000 calls / month
- 1 requests / second
- Hard cap (429 above quota, no overage)
- 1,000 calls/month
- 1 req/sec
- All 30+ voices
- No credit card
Starter
€5.00 /month
- 30,000 calls / month
- 5 requests / second
- Hard cap (429 above quota, no overage)
- 30k calls/month
- 5 req/sec
- WAV + base64 output
- Email support
Pro
€19.00 /month
- 200,000 calls / month
- 20 requests / second
- Hard cap (429 above quota, no overage)
- 200k calls/month
- 20 req/sec
- Speed/pitch control
- Priority support
Enterprise
€99.00 /month
- 2,000,000 calls / month
- 50 requests / second
- Hard cap (429 above quota, no overage)
- 2M calls/month
- 50 req/sec
- Bulk audio generation
- Dedicated SLA
Built by
Related APIs
Other APIs with overlapping tags.
Audius API
Audius as an API — the decentralised music streaming platform, returned as clean JSON, no key. Search tracks, artists and playlists; pull trending tracks by genre and time window; look up a track (genre, mood, bpm, musical key, ISRC, play/favourite/repost counts, artwork and a durable stream URL), an artist (followers, track and playlist counts, bio, location) by id or @handle, an artist's own tracks, and a playlist or album with its full track list. Every track comes with a ready-to-play stream URL and a preview URL. Live data straight from the Audius discovery network. Distinct from mainstream catalogues: Audius is an independent, creator-owned catalogue of electronic, hip-hop and underground music with actual streamable audio — ideal for music-discovery apps, players, DJ tools and Web3 music projects. 8 data endpoints. Authenticated with an x-oanor-key; fair-use rate limits per plan.
api.oanor.com/audius-api
Mixcloud API
Mixcloud as an API — the home of long-form audio: DJ mixes, radio shows and podcasts, returned as clean JSON, no key. Search cloudcasts, users or tags; look up a user profile (followers, listens, location, picture) and their shows; get a cloudcast's full detail — play count, favourites, reposts, listener count, audio length, tags and uploader; read a show's comments; pull the trending cloudcasts for any tag or category; and list Mixcloud's categories. Live data straight from Mixcloud's public API. Distinct from track-based music APIs: Mixcloud is hour-long mixes, broadcast archives and shows — ideal for music-discovery apps, radio and DJ directories, podcast tools and audio dashboards. 8 data endpoints. Authenticated with an x-oanor-key; fair-use rate limits per plan.
api.oanor.com/mixcloud-api
Vinyl Record API
Vinyl-record geometry maths as an API, computed locally and deterministically — the playing-time, groove-length and groove-speed numbers a cutting engineer, pressing plant or audio hobbyist works a record out with. The playing-time endpoint gives a side's maximum time = the number of groove turns ÷ the turntable speed, where the turns = the recorded band's radial width ÷ the groove pitch (the spacing between adjacent grooves): a 12-inch LP with ~85 mm of band at a 100 µm pitch holds about 850 turns, so at 33⅓ rpm that is roughly 25 minutes a side — a tighter pitch fits more time but cuts groove amplitude and so loudness and bass, the classic time-versus-level trade. The groove-length endpoint unrolls the spiral: length ≈ turns × the mean circumference (π × the average of the outer and inner diameters), on the order of 400–500 metres for an LP side, the whole of which the stylus traces once. The groove-speed endpoint gives the linear speed under the stylus = 2π × rpm/60 × radius, so the outer grooves of an LP pass at about 50 cm/s but the inner ones only ~20 cm/s — the cause of inner-groove distortion and why engineers place quieter tracks last. Everything is computed locally and deterministically, so it is instant and private. Ideal for record-cutting and mastering tools, hi-fi and collector apps, and audio-engineering calculators. Pure local computation — no key, no third-party service, instant. 3 compute endpoints. For musical note and tempo maths use a music API.
api.oanor.com/vinyl-api
Helmholtz Resonator API
Helmholtz-resonator acoustics as an API, computed locally and deterministically. The frequency endpoint computes the resonant frequency of a Helmholtz resonator — a cavity with a neck, like a bottle or a ported speaker box — from the neck area (or diameter), the neck length and the cavity volume, f = (c/2π)·√(A/(V·L_eff)), adding the acoustic end correction (about 0.85·radius for a flanged end and 0.61·radius for a free end) so a short or open neck resonates lower than its physical length suggests. The design endpoint inverts the relation, V = A·c²/(L_eff·ω²), to give the cavity volume needed to tune a resonator or a muffler chamber to a target frequency. The port-tuning endpoint sizes a bass-reflex (vented loudspeaker) box port in practical audio units — from the box volume in litres and the port diameter in centimetres it gives the tuning frequency for a given port length, or the port length required for a target tuning frequency, using the 0.732·diameter end correction. Core endpoints use SI units; the speed of sound defaults to 343 m/s. Everything is computed locally and deterministically, so it is instant and private. Ideal for audio, loudspeaker-design, musical-instrument, muffler and acoustic-treatment app developers, bass-reflex and resonator tools, and acoustics education. Pure local computation — no key, no third-party service, instant. Live, nothing stored. 3 endpoints. This is Helmholtz resonance; for room reverberation use a reverberation API and for standing waves on strings and in pipes a standing-wave API.
api.oanor.com/helmholtz-api
Frequently asked questions
Quick answers about pricing, quotas, and integration.
How do I get an API key for Text-to-Speech API?
What's the rate limit for Text-to-Speech API?
How much does Text-to-Speech API cost?
Can I cancel my subscription anytime?
Is Text-to-Speech API GDPR-compliant?
Pick an endpoint from the list on the left to see its details and try it.
Code snippets
Sign up to get an API key, then call any path under your slug.
curl https://api.oanor.com/tts-api/SOME_PATH \
-H "x-oanor-key: oanor_test_..."
const res = await fetch("https://api.oanor.com/tts-api/SOME_PATH", {
headers: { "x-oanor-key": "oanor_test_..." }
});
const data = await res.json();
$ch = curl_init("https://api.oanor.com/tts-api/SOME_PATH");
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_HTTPHEADER, ["x-oanor-key: oanor_test_..."]);
$response = curl_exec($ch);
import requests
r = requests.get(
"https://api.oanor.com/tts-api/SOME_PATH",
headers={"x-oanor-key": "oanor_test_..."},
)
print(r.json())
Ratings
Sign in to rate.
No reviews yet.
Discussion
Ask questions, share usage tips, get answers from the provider and other developers. Public — anyone can read.
Sign in to start a thread or reply.
Sign inNew thread
·
-
Provider answer
🔒 This thread is locked — no new replies.
-
·
- No threads yet — start the discussion.
Support
Private 1:1 support with the provider — billing questions, integration issues, account problems. Only you and the provider team can see these threads.
Sign in to open a support ticket.
Sign inOpen new ticket
Describe what you need help with. The provider team gets an email and replies on the ticket page.
-
·
Urgent - No tickets yet for this API.