Back to Models
GPT-4o Mini TTS
openaiopenai/gpt-4o-mini-tts
Media Generation Capabilities
tts
- output_formats
- mp3
- opus
- aac
- flac
- voices
- alloy
- ash
- ballad
- coral
- echo
- fable
- onyx
- nova
- sage
- shimmer
- verse
- defaults
- voice
- alloy
API guide
Text-to-speech (streaming)
GPT-4o Mini TTS uses the standard OpenAI speech endpoint. Call it via TheRouter's unified API β the model supports synchronous and streaming modes with steerable instructions for tone control.
cURL
curl https://api.therouter.ai/v1/audio/speech \
-H "Authorization: Bearer $THEROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-4o-mini-tts",
"input": "Welcome to TheRouter β your unified API for all AI models.",
"voice": "nova",
"instructions": "Speak warmly and professionally, like a friendly customer service agent.",
"response_format": "mp3"
}' \
--output speech.mp3Streaming TTS
For real-time voice applications, stream audio chunks as they are generated. GPT-4o Mini TTS sends binary audio chunks via SSE, with the first chunk arriving in under 500ms in typical conditions.
cURL
curl https://api.therouter.ai/v1/audio/speech \
-H "Authorization: Bearer $THEROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-4o-mini-tts",
"input": "This is a streaming voice demo using TheRouter API.",
"voice": "echo",
"response_format": "pcm"
}' \
--output - | ffplay -f s16le -ar 24000 -ac 1 -Fact ledger β every claim on this page traces here
| source | URL | retrieved | |
|---|---|---|---|
| Release date | openai.com β | 2026-05-28 | verified |
| Base architecture | openai.com β | 2026-05-28 | verified |
| Endpoint | developers.openai.com β | 2026-05-28 | verified |
| Voices | docs.aimlapi.com β | 2026-05-28 | verified |
| Supported languages | tokenmix.ai β | 2026-05-28 | verified |
| Context window | tokenmix.ai β | 2026-05-28 | to verify |
| Output formats | developers.openai.com β | 2026-05-28 | verified |
| Steerability | simonwillison.net β | 2026-05-28 | verified |
| Steerability benchmark (Simon Willison) | simonwillison.net β | 2026-05-28 | verified |
| Standard TTS benchmarks | openai.com β | 2026-05-28 | unknown |
| OpenAI launches gpt-4o-mini-tts alongside new speech-to-text models | openai.com β | 2026-05-28 | verified |
| What voices are available with gpt-4o-mini-tts? | docs.aimlapi.com β | 2026-05-28 | to verify |
| How does the instructions parameter work? | simonwillison.net β | 2026-05-28 | to verify |
| What languages does gpt-4o-mini-tts support? | tokenmix.ai β | 2026-05-28 | to verify |
| How does pricing work exactly? Token-based vs per-minute? | tokenmix.ai β | 2026-05-28 | to verify |
| Can I use gpt-4o-mini-tts through TheRouter? | api.therouter.ai β | 2026-05-28 | to verify |