Station identity is the voice a channel is recognised by, heard between programmes rather than inside them. It is a narrow register: short, measured, and the same every time.
Free to start!
German AI Voices
Female Voices
Warm Voices
AI Voices for Podcast Generation
British English AI Voices
AI Voices for Documentary Voice Over
Calm Voices
Australian English AI Voices
AI Voices for Gaming & Character Voices
Professional Voices
AI Narrator Voices
Cheerful Voices
AI Voices for Customer Support Automation
Authoritative Voices
AI Voices for Meditation & Wellness
Gravelly AI Voices
AI Voices for YouTube Voiceover
Indian English AI Voices
AI Voices for Movie Trailers
Friendly Voices
Narration is the one job where a voice has to hold up for hours rather than seconds. 163 of the 244 voices here carry the narration tag, the largest group in the catalog, across English, Hindi and nine other Indic languages.
1500+ voices to explore
Browse our full voice library and find the right tone, accent, and personality for your agent.
Model Specifications
Streaming transports
Output formats
Speed range
Sample rate
Latency
Continuity is a register of its own
A channel ident is six words. A continuity link is twenty. Neither reports news nor sells anything, which is what separates this from a newsroom read or a commercial. The job is recognition: a viewer should know the channel from the voice before the logo appears, which puts consistency above expression.
Promos run to the second
Network promos are cut to fixed durations and the voice has to land inside them. Speed adjusts from 0.5 to 2.0, so a line that runs two seconds long is fixed by the setting rather than by rewriting. Requests cap at 250 characters, roughly one continuity link, so you generate line by line and retime individually.
The same voice, for years
Station voices traditionally last a decade, which is why rebooking one for every schedule change is expensive and why most channels under-produce their continuity. Generated idents cost one request each, so a seasonal refresh or a new programme strand stops being a budget line.
Delivering to a playout system
Output is 44.1 kHz mono as WAV, MP3 or raw PCM. Take WAV into playout, since broadcast chains apply their own compression and loudness normalisation on ingest. Confirm the loudness specification your channel runs to, as that is applied before delivery rather than by the API.
Similar to
AI Broadcast Voices
AI News Anchor Voices
News delivery is judged on clarity before character. These six come from voices carrying both the narration and educational tags, the combination that suits reading information aloud rather than performing it.
AI Voices for Announcements & Public Transport
Announcements are heard in reverberant halls and repeated thousands of times. Pronunciation dictionaries fix station and place names permanently, ulaw and alaw feed public address hardware directly, and one voice carries a full multilingual chain.
AI Sports Announcer Voices
Commentary is the one narration job that happens while the thing it describes is still happening. These six carry pace and projection, and generation runs fast enough to keep up with live play.
AI Voices for Radio Ads
A thirty second radio spot is one or two requests and about two seconds of generation. These six come from the 57 voices tagged for advertisement, chosen for projection and pace.
AI Voices for Ads & Commercials
Commercial reads are short, fast, and worth testing in variants. A thirty second spot is one or two requests, which makes producing four versions cheaper than booking one session.
AI Voices for Documentary Voice Over
Documentary narration works by staying out of the way. The voice carries information the picture cannot, without competing with it. These six are drawn from the 163 narration-tagged voices, chosen for an even, unhurried delivery.
