xAI STT v1 — Reelina AI Âm thanh
ISO 639-1 language code (Filipino uses 'fil'). The model transcribes speech in any supported language regardless of this parameter — setting it, together with text_normalization=true, enables formatting of numbers, currencies, and units into their written form for that language. Leave unset for automatic language detection.
When true, enables Inverse Text Normalization — converts spoken-form numbers/currency into written form (e.g. "one hundred dollars" to "$100"). This controls text formatting of the transcript, not the audio format.
When true, enables speaker diarization. Each word in the result includes a speaker_id field identifying the detected speaker.
When true, transcribes each audio channel independently.
When true, filler words (e.g. "um", "uh") are included in the transcription; when false (default), they are automatically removed.
Key terms to bias transcription toward (e.g. product names). Up to 100 terms, each up to 50 characters.
Format hint for raw/headerless audio. Auto-detected for container formats (such as mp3, wav, etc), set the value to 'auto'.
Sample rate in Hz. Only required for raw audio (pcm, mulaw, alaw).
Number of audio channels (2–8). Only required for multichannel raw audio. Auto-detected for container formats.
About xAI STT v1
xAI STT v1 is a production-grade speech-to-text model that transcribes audio into accurate, formatted text. It supports 24+ languages with automatic language detection, word-level timestamps, speaker diarization, multichannel transcription, and inverse text normalization.
Specifications
| Provider | xAI |
|---|---|
| Type | Audio generation |
| Cost per run | 1 credits |
| Input | Text prompt |
Alternatives to xAI STT v1
Models in this workspace that do the same job, closest in price first. Your credit balance works across all of them.
Frequently asked questions
- What is xAI STT v1?
- xAI STT v1 is a production-grade speech-to-text model that transcribes audio into accurate, formatted text. It supports 24+ languages with automatic language detection, word-level timestamps, speaker diarization, multichannel transcription, and inverse text normalization.
- How much does xAI STT v1 cost?
- xAI STT v1 costs 1 credits per run, deducted from your Reelina balance. The exact cost is shown before you press Generate, and one balance covers every model — there is no separate subscription per model.
- What do I need to use xAI STT v1?
- A text prompt describing what you want. No upload needed.
- Can I use the results commercially?
- Your generations are yours to use, subject to our terms and acceptable use policy. For anything business-critical, check the licence of the specific model you pick.
- How long are my files kept?
- Tệp tải lên chỉ được dùng để tạo ra kết quả của bạn. Các nội dung được tạo ở chế độ riêng tư theo mặc định và mọi thứ sẽ bị xóa sau một tuần kể từ khi được tạo.
Looking for something else? Browse every model.